Class XII Artificial Intelligence (843)

Minimum Learning Support Material · CBSE 2026-27

Notes · Numericals with working · 889 solved questions · Flashcards · Quiz · Practice Paper Maker

Designed by NareN, PGT (Computer Science), PM SHRI K V Shalimar Bagh, Delhi-88 (Shift-I) ✨ Click Here For Your Valuable Feedback ✨
1

Know the paper first

CBSE Sample Question Paper 2026-27: 21 questions, 50 marks, 2 hours

QuestionWhat comesAttemptMarks
Q16 objective questions on Employability Skillsany 41 x 4 = 4
Q2 to Q56 objective questions each on the AI units (MCQ, True/False, Assertion-Reason, match, small numericals)any 5 in each4 x 5 = 20
Q6 to Q10Employability Skills, 20 to 30 words eachany 3 of 52 x 3 = 6
Q11 to Q16one question from each AI unit, 20 to 30 words eachany 4 of 62 x 4 = 8
Q17 to Q21Units 2, 5, 6, 7 and 8, 50 to 80 words eachany 3 of 54 x 3 = 12

The paper has 21 questions and is of 2 hours. You answer 15 questions: all of Q1 to Q5 (with the choice inside each) and 10 out of Q6 to Q21.

Unit-wise marks in the theory paper (50)

Unit 1 (Python Programming-II) and Unit 4 (AI with Orange Data Mining Tool) are assessed in the practical only.

Blueprint of the paper

One common blueprint, as per the CBSE Sample Question Paper 2026-27. All the practice papers of this kit follow it. Each cell shows the number of questions given from that unit.

Unit1mark2marks4marksTotalquestions
Part ACommunication Skills-IV11-2
Part ASelf-Management Skills-IV21-3
Part AICT Skills-IV11-2
Part AEntrepreneurial Skills-IV11-2
Part AGreen Skills-IV11-2
Part BUnit 2: Data Science Methodology5117
Part BUnit 3: Making Machines See51-6
Part BUnit 5: Big Data and Data Analytics3115
Part BUnit 6: Understanding Neural Networks5117
Part BUnit 7: Generative AI3115
Part BUnit 8: Data Storytelling3115
Questions given3011546
To be answered247334
Marks24141250

Numericals to practise

2 or 4 marksConfusion matrix: accuracy, precision, recall, F1Unit 2
2 or 4 marksMSE and RMSE from actual and predicted valuesUnit 2
1 to 4 marksNeuron: weighted sum, bias, ReLU outputUnit 6
1 markk-fold cross validation: size of each foldUnit 2
1 markPixels and bytes of an imageUnit 3
1 markUnits of data: GB, TB, PBUnit 5

Practical: 50 marks

2

Pass plan in three steps

Where the 50 marks come from, easiest first

Step 1 · 10 marksEmployability Skills: definitions and lists only. Learn the five small tables in section 3.
Step 2 · 17 marksUnits 7, 8 and 5: Generative AI, Data Storytelling and Big Data. Short theory with fixed lists: the 6 Vs, the four steps of analytics, GAN, LLM, Freytag's Pyramid.
Step 3 · 23 marksUnits 2, 6 and 3: the ten steps of the methodology, MSE and RMSE, confusion matrix, layers of a neural network, the five stages of computer vision.
Marks milne wali baat
  • You have a choice in every question. Read all the parts first and pick the ones you are sure of.
  • In a numerical, write the formula first, then the values.
  • Keep 2-mark answers to 20-30 words and 4-mark answers to 50-80 words. Use points.
Common mistake
  • Extracting data is Data Collection, not Data Requirements.
  • Edge detection is feature extraction, not preprocessing.
  • Veracity is trust; Velocity is speed; Variety is types.
  • Log loss is for classification; MSE is for regression.
3

Part A: Employability skills

10 marks · five units · detailed chapters

Unit 1: Communication Skills-IV

1.1 Communication at Level IV

Effective communication at work is not only speaking well - it is also listening well, writing correctly and choosing the right words. This chapter covers active listening, parts of speech, sentence types, active and passive voice and capitalisation.

1.2 Hearing vs listening

Hearing and listening
Hearing
  • physical - the ear receives sound
  • automatic
  • no effort
  • we hear traffic noise
VS
Listening
  • mental - understanding the meaning
  • deliberate
  • needs attention
  • we listen to a teacher's instructions

Active listening is listening with full attention, understanding the message, remembering it and responding thoughtfully. A good listener makes the speaker feel valued and avoids mistakes caused by misunderstanding.

1.3 Stages of active listening

Five stages of active listening
1Receiving - hear the message
➜
2Understanding - grasp the meaning
➜
3Remembering - store it
➜
4Evaluating - judge facts and opinions
➜
5Responding - give feedback
StageWhat happensExample: a doctor's advice
Receivingpaying attention to the sounds and signalsyou hear "take one tablet twice a day"
Understandinginterpreting the wordsyou understand: morning and night
Rememberingkeeping it in memoryyou note it in your phone
Evaluatingthinking about it critically"Should I take it before or after food?"
Respondingverbal or non-verbal replyyou ask the doctor and nod

1.4 RESPECT: a guide to active listening

RESPECT
📵
R - Remove distractions

phone away, face the speaker

👀
E - Eye contact

look at the speaker

🙂
S - Show you are listening

nod, smile, "I see"

🎯
P - Pay attention

focus on the words and feelings

💛
E - Empathise

understand the speaker's point of view

❓
C - Clarify doubts

ask questions, paraphrase

🎚️
T - Tune yourself to the speaker

adjust to their pace and tone

Barriers to active listening

BarrierExample
Distractionsphone notifications, noise
Prejudice"This person never says anything useful"
Interruptingcompleting the speaker's sentences
Daydreamingthinking about something else
Preparing your replynot hearing the full message
Information overloadtoo much information at once
Paraphrasing to confirm

Manager: "Send the revised budget to finance by Thursday noon and copy me." Employee: "So, I'll e-mail the revised budget to finance before 12 on Thursday with you in CC. Right?" Paraphrasing shows listening and avoids errors.

1.5 Parts of speech

Eight parts of speech
Parts of speech
Noun
Pronoun
Verb
Adjective
Adverb
Preposition
Conjunction
Interjection
PartFunctionExample
Nounnaming wordAnil works in Pune.
Pronounreplaces a nounHe likes it.
Verbaction / stateShe presented the report.
Adjectivedescribes a nouna detailed report
Adverbdescribes a verb, adjective, adverbspoke confidently
Prepositionshows relationthe file on the desk
Conjunctionjoinsfast but careful
InterjectionemotionHurray! We won.

Types of nouns

TypeExample
ProperIndia, Ravi, Monday
Commoncity, boy, day
Collectiveteam, class, herd
Abstracthonesty, courage, joy
Materialgold, wood, cotton

1.6 Sentence types and parts

TypeFunctionExample
Statement (declarative)gives informationThe exam begins at ten.
Question (interrogative)asks somethingWhen does the exam begin?
Emotion (exclamatory)shows strong feelingWhat a wonderful result!
Order (imperative)command or requestPlease open your books.

A sentence has a subject (who / what) and a predicate (what the subject does). Many sentences also have an object (who / what receives the action): *The team (subject) won (verb) the trophy (object).*

1.7 Active and passive voice

Voice
Active
  • doer comes first
  • direct and clear
  • "Ravi wrote a letter."
VS
Passive
  • action / receiver comes first
  • uses 'be' + past participle
  • "A letter was written by Ravi."
TenseActivePassive
Simple presentShe writes reports.Reports are written by her.
Simple pastThe chef cooked the meal.The meal was cooked by the chef.
FutureThey will open the shop.The shop will be opened by them.
Present continuousHe is painting the wall.The wall is being painted by him.
Remember

Use active voice for clear, direct business writing. Use passive voice when the doer is unknown or less important: "The road was repaired last week."

1.8 Capitalisation and punctuation

MINTS - when to use capital letters
📅
M - Months and days

March, Monday

🙋
I - the pronoun I

"I am ready."

🏷️
N - Names

Priya, Delhi, the Ganga, Infosys

🎓
T - Titles

Dr. Sharma, Prime Minister

🔠
S - Starting letter

first word of every sentence

MarkUseExample
Full stop (.)end of a statementThe bus left.
Comma (,)pause; listspens, pencils, files
Question mark (?)questionAre you ready?
Exclamation (!)strong feelingGreat job!
Apostrophe (')possession / contractionRiya's bag; don't
Quotation marks (" ")exact wordsHe said, "Wait."

1.9 Exam-ready answers

Q. Write the five stages of active listening. (2 marks)

Receiving, understanding, remembering, evaluating and responding.

Q. Change into passive voice: (i) The manager approved the plan. (ii) Students are cleaning the classroom. (2 marks)

(i) The plan was approved by the manager. (ii) The classroom is being cleaned by the students.

Unit 2: Self-Management Skills-IV

2.1 Self-management at Level IV

At Level IV, self-management focuses on motivation and positive attitude, result orientation, self-awareness and personality. These help a young person succeed in higher studies and the workplace.

Self-management IV
Self-management
Motivation
Positive attitude
Result orientation
Self-awareness
Personality (Big Five)

2.2 Motivation

Motivation is the internal or external force that starts, directs and keeps up our behaviour towards a goal.

Two kinds of motivation
Intrinsic (internal)
  • joy of doing
  • curiosity and interest
  • long-lasting
  • e.g. coding because you love solving problems
VS
Extrinsic (external)
  • rewards, marks, money, praise
  • fear of punishment
  • may stop when reward stops
  • e.g. studying only for a prize

Maslow's hierarchy of needs

Maslow's needs (top to bottom)
Self-actualisation - reaching full potential
Esteem - respect, recognition
Love and belonging - friends, family
Safety - security, job, health
Physiological - food, water, sleep

People are motivated first by basic needs; when those are met, higher needs motivate them. A worker who has a secure job (safety) may next be motivated by recognition (esteem).

2.3 Positive attitude

A positive attitude is a way of thinking that focuses on solutions and possibilities. It improves health, relationships and performance.

Ways to keep a positive attitude
🙏
Gratitude

note what is going well

🗣️
Positive self-talk

"I can learn this"

👥
Good company

spend time with positive people

🏃
Healthy routine

exercise, sleep, good food

🎯
Focus on solutions

ask "What can I do now?"

😊
Help others

kindness improves mood

2.4 Result orientation

Result orientation means focusing on achieving the desired outcome, not only on doing activities. A result-oriented person sets clear goals, plans, uses the right tools, tracks progress and finishes on time.

Steps of result orientation
1Set a clear goal
➜
2Make an action plan
➜
3Use the right tools and resources
➜
4Work within the time
➜
5Measure the result
➜
6Improve
Result-oriented student

Goal: score 90 in AI. Plan: one chapter a week, 20 questions daily from the kit, a weekly sample paper. Tools: notes, question bank, timer. Track: marks in each sample paper. Improve: re-study weak chapters. Focus stays on the result - 90 marks - not just on "hours studied".

2.5 Self-awareness

Self-awareness is the clear understanding of our own personality, strengths, weaknesses, thoughts, beliefs, emotions and motivations.

AspectQuestionBenefit
StrengthsWhat am I good at?choose suitable careers
WeaknessesWhat do I need to improve?plan training
EmotionsWhat triggers my anger or stress?better self-control
ValuesWhat is important to me?right decisions

Ways: reflection and journaling, feedback from others, personality tests, meditation, trying new experiences.

2.6 Personality and the Big Five

Personality is the set of qualities - thoughts, feelings and behaviour patterns - that make a person unique. Psychologists describe it with the Big Five (OCEAN) factors:

Big Five personality factors (OCEAN)
🎨
Openness

curious, creative, likes new ideas (low: prefers routine)

📋
Conscientiousness

organised, careful, dependable (low: careless)

🎉
Extraversion

outgoing, energetic, talkative (low: reserved)

🤗
Agreeableness

kind, helpful, cooperative (low: competitive)

🌊
Neuroticism

anxious, easily upset (low: calm and stable)

FactorWorkplace example
High opennessdesigner who tries new styles
High conscientiousnessaccountant who never misses deadlines
High extraversionsalesperson who enjoys meeting people
High agreeablenessnurse who cares for patients
Low neuroticismair-traffic controller who stays calm under pressure

2.7 Personality disorders (awareness)

A personality disorder is a long-lasting pattern of thinking and behaviour that is very different from what is expected and causes difficulties in daily life and relationships. They are diagnosed only by qualified professionals; the CBSE book groups them into three clusters:

ClusterDescriptionDisorders
A - odd, suspiciousunusual thinkingparanoid, schizoid, schizotypal
B - emotional, impulsivedramatic, unstable behaviourantisocial, borderline, histrionic, narcissistic
C - anxious, fearfulworry and fearavoidant, dependent, obsessive-compulsive
Common mistake

This is for awareness only. We must never label classmates or others; if someone is struggling, encourage them to talk to a counsellor or doctor.

2.8 Developing a healthy personality

  • Practise good habits: punctuality, cleanliness, courtesy.
  • Build communication and social skills.
  • Manage stress through exercise, hobbies and rest.
  • Seek feedback and keep learning.

2.9 Exam-ready answers

Q. Differentiate between intrinsic and extrinsic motivation. (2 marks)

Intrinsic motivation comes from within, such as interest and enjoyment of the task. Extrinsic motivation comes from outside, such as rewards, marks or praise.

Q. Explain the Big Five personality factors. (4 marks)

Openness - curiosity and creativity; Conscientiousness - being organised and responsible; Extraversion - being outgoing and energetic; Agreeableness - being kind and cooperative; Neuroticism - tendency to feel anxious or upset (low neuroticism means emotional stability).

Unit 3: ICT Skills-IV

3.1 Spreadsheets

A spreadsheet is application software that stores data in rows and columns and performs calculations, analysis and charts. Examples: LibreOffice Calc (.ods), Microsoft Excel (.xlsx), Google Sheets.

Uses of spreadsheets
💰
Budgets

household and business accounts

📊
Marks analysis

totals, averages, ranks of students

📦
Inventory

stock in a shop

🧾
Salary sheets

pay and deductions

📈
Charts

sales trends, survey results

3.2 Basic terms

TermMeaning
Workbookthe whole file
Worksheetone sheet (tab) in the workbook
Rowhorizontal line, numbered 1, 2, 3 ...
Columnvertical line, lettered A, B, C ...
Cellmeeting point of a row and column
Cell addresscolumn letter + row number, e.g. B5
Rangea group of cells, e.g. A1:A10
Active cellthe selected cell (thick border)

3.3 Entering data and formulas

Types of data: text (labels), numbers, dates, formulas.

A formula always starts with =: =B2+C2, =A1*10%. Operators: + - * / ^ (power).

Order of operations (BODMAS)
1Brackets ()
➜
2Power ^
➜
3Multiplication and division
➜
4Addition and subtraction
Calculating totals

Marks in B2 = 78, C2 = 85, D2 = 90. In E2: =B2+C2+D2 gives 253; in F2: =E2/3 gives 84.33. Copying E2 down with the fill handle repeats the formula for every student using relative references.

Cell references

TypeExampleOn copying
RelativeA1changes with position
Absolute$A$1never changes
Mixed$A1 or A$1only one part changes

3.4 Functions

FunctionPurposeIf A1 = 20, A2 = 30, A3 = 50
=SUM(A1:A3)total100
=AVERAGE(A1:A3)mean33.33
=MAX(A1:A3)largest50
=MIN(A1:A3)smallest20
=COUNT(A1:A3)how many numbers3
=IF(A1>=33,"Pass","Fail")conditionPass
=ROUND(33.333,1)rounding33.3

3.5 Sorting, filtering and formatting

Sort vs filter
Sort
  • arranges rows in order (A-Z, smallest to largest)
  • all rows remain visible
  • Data > Sort
VS
Filter
  • shows only rows that meet a condition
  • other rows are hidden, not deleted
  • Data > AutoFilter

Formatting: number format (currency, percentage, date), bold headings, borders, fill colour, conditional formatting (e.g. marks below 33 in red), merge and centre for titles, wrap text, freeze panes to keep headings visible.

3.6 Charts

Choose the right chart
📊
Column / bar

compare items: marks of students

📈
Line

trend over time: monthly sales

🥧
Pie

parts of a whole: expense share

✴️
Scatter (XY)

relation between two variables

Steps: select data > Insert > Chart > choose type > add title, axis labels and legend.

3.7 Protecting a spreadsheet

  • Protect sheet (Tools > Protect Sheet): stops others from changing cells; a password can be set.
  • Protect document / workbook: stops adding, deleting or renaming sheets.
  • Password to open: File > Save As > Save with password.

3.8 Presentation software

Presentation software creates slides with text, pictures, charts, audio, video and animation for talks and lessons. Examples: LibreOffice Impress (.odp), Microsoft PowerPoint (.pptx), Google Slides.

Making a presentation
1Plan the content
➜
2Choose a design / template
➜
3Add slides and layouts
➜
4Insert text, images, charts
➜
5Add transitions and animation
➜
6Rehearse
➜
7Present (F5)
FeatureUse
Slide layouttitle slide, title and content, two content, blank
Slide mastersame design on all slides
Transitioneffect when moving to the next slide
Animationeffect on an object within a slide
Viewsnormal, outline, notes, slide sorter, slide show
Speaker notesnotes for the presenter
F5 / Shift + F5start from the first / current slide
Good slides

one idea per slide, about 6 lines with 6 words each, large readable fonts, contrasting colours, pictures instead of long text.

3.9 Exam-ready answers

Q. What is the difference between sorting and filtering? (2 marks)

Sorting arranges all rows in ascending or descending order. Filtering shows only the rows that meet a condition and hides the others temporarily.

Q. Write the result of the formulas if A1 = 10, A2 = 25, A3 = 40: (i) =SUM(A1:A3) (ii) =AVERAGE(A1:A3) (iii) =MAX(A1:A3) (iv) =COUNT(A1:A3). (4 marks)

(i) 75 (ii) 25 (iii) 40 (iv) 3.

Unit 4: Entrepreneurial Skills-IV

4.1 Entrepreneurship and the entrepreneur

Entrepreneurship is the process of creating a new venture by identifying an opportunity, arranging resources and taking risks, in order to earn profit and add value to society. The person is the entrepreneur; the venture is the enterprise.

Entrepreneurial process
1Identify the opportunity
➜
2Develop the idea
➜
3Plan (business plan)
➜
4Raise resources
➜
5Start and manage
➜
6Grow or exit

4.2 Types of entrepreneurs (by business)

Types of entrepreneurs
🛎️
Service

sells services: salon, courier, coaching

🛍️
Business / trading

buys and sells: grocery, wholesale

🏭
Industrial

manufactures goods: textile mill, food processing

🌾
Agricultural

farming and allied: dairy, poultry, horticulture

⚙️
Technical

technology-based: software, app, electronics

🤝
Social

solves social problems: affordable healthcare

4.3 Entrepreneurial competencies

CompetencyMeaningExample
Decisivenesstakes timely, firm decisionschooses a supplier after comparing quotes
Initiativeacts without being toldstarts home delivery before competitors
Interpersonal skillsbuilds good relationskeeps customers and staff happy
Perseverancekeeps going after setbacksrelaunches after the first product fails
Organisational skillsplans and uses resources wellmanages stock, cash and staff schedules

4.4 Barriers to entrepreneurship

Barriers
Barriers
Environmental - raw material, labour, roads, power
Financial - no capital or loans
No or faulty business plan
Personal - self-doubt, fear of failure
Social - family pressure for a job
Legal - many permissions
BarrierExampleHow to overcome
Environmentalno good roads or electricity in the areachoose a suitable location, solar power
No / faulty business planno study of costs or customersprepare a proper plan with market research
Personalfear of failure, low confidencetraining, mentors, start small
Financialno money to startsavings, Mudra loan, investors

4.5 Entrepreneurial attitudes

  • Takes calculated risks.
  • Believes in self and in the idea.
  • Is open to new ideas and feedback.
  • Sees a problem as an opportunity.
  • Is independent yet a team player.
  • Learns continuously.
Problem as opportunity

During water shortages in a town, Kiran sets up a small RO water plant and supplies 20-litre cans to homes and offices. A problem for many became her business opportunity.

4.6 The business plan

A business plan is a written document that describes the business idea, the market, operations and finances. It guides the entrepreneur and convinces banks and investors.

Parts of a business plan
1Executive summary
➜
2Business description
➜
3Market analysis
➜
4Products and services
➜
5Marketing plan
➜
6Operations
➜
7Financial plan
PartAnswers
Executive summaryWhat is the business in short?
Market analysisWho are the customers and competitors?
Marketing planHow will we reach customers? (4 Ps: Product, Price, Place, Promotion)
OperationsWhere and how will we produce and deliver?
Financial planHow much money is needed? Expected sales, costs and profit?

Break-even point

Break-evenBreak-even units = Fixed costs / (Selling price per unit - Variable cost per unit)
Break-even calculation

A candle maker has fixed costs (rent, machine) of Rs 12,000 a month. Each candle sells for Rs 50 and costs Rs 30 to make. Break-even = 12,000 / (50 - 30) = 600 candles. Selling more than 600 candles a month gives profit.

4.7 Support for entrepreneurs in India

SchemeSupport
Startup Indiatax benefits, easy registration, funding support
PM Mudra Yojanaloans: Shishu (up to Rs 50,000), Kishor, Tarun
Stand-Up Indialoans for SC/ST and women entrepreneurs
Atal Innovation Missionincubation centres, tinkering labs
Udyam registrationeasy MSME registration

4.8 Case study: a social entrepreneur

Case study: SELCO India

Harish Hande saw that millions of rural homes had no reliable electricity. In 1995 he started SELCO to provide solar lighting to poor families, working with banks so that customers could pay in small instalments. SELCO has lit lakhs of homes, reduced kerosene use and created local jobs for technicians. It shows initiative, perseverance and the social type of entrepreneurship.

Qualities seen in successful founders
🎯
Clear vision

knows the problem to solve

🔁
Perseverance

continued for years before success

🤝
Partnerships

worked with banks and communities

💡
Innovation

new payment and service models

4.8 Exam-ready answers

Q. Name any four types of entrepreneurs with examples. (2 marks)

Service (salon), trading (grocery store), industrial (food-processing unit), agricultural (dairy farm), technical (software company), social (low-cost healthcare). (Any four.)

Q. Explain any four barriers to entrepreneurship. (4 marks)

Environmental barriers - lack of raw material, labour, roads; no or faulty business plan; personal barriers - fear of failure and self-doubt; financial barriers - lack of capital. Others: social pressure, legal formalities.

Unit 5: Green Skills-IV

5.1 Green jobs

Green jobs are decent jobs that help protect or restore the environment - by saving energy and raw materials, reducing greenhouse-gas emissions, minimising waste and pollution, and protecting ecosystems (International Labour Organization).

Benefits of green jobs
Green jobs
Limit greenhouse gases
Reduce waste and pollution
Protect ecosystems
Use energy and materials efficiently
Help adapt to climate change

5.2 Fields of green jobs

Green job sectors
🌾
Agriculture

organic farming, soil health, drip irrigation

🚌
Transportation

electric vehicles, CNG, metro, cycling

💧
Water conservation

rainwater harvesting, watershed, recycling

☀️
Renewable energy

solar, wind, small hydro, biogas

🏞️
Eco-tourism

nature tourism that protects local ecology

🏗️
Green construction

energy-efficient, GRIHA-rated buildings

🗑️
Solid waste management

segregation, composting, recycling

🔧
Appropriate technology

simple, local, low-cost tools (solar dryers)

FieldGreen jobWhat they do
Agricultureorganic farming advisorguides farmers to use natural inputs
TransportEV technicianmaintains electric vehicles and chargers
Waterrainwater harvesting technicianbuilds and maintains RWH systems
Energysolar PV installerinstalls rooftop and grid solar panels
Tourismeco-tour guideleads nature tours responsibly
Constructiongreen building consultantdesigns buildings that save energy and water
Wastewaste-management supervisorruns segregation and recycling

5.3 Greenhouse gases and climate change

Greenhouse gases (GHGs) trap heat in the Earth's atmosphere. The main ones are carbon dioxide (CO2), methane (CH4), nitrous oxide (N2O), water vapour and fluorinated gases. Oxygen and nitrogen are not greenhouse gases.

How climate change happens
1Burning fossil fuels and cutting forests
➜
2More greenhouse gases
➜
3More heat trapped
➜
4Global warming
➜
5Climate change - floods, droughts, heatwaves, sea-level rise
GasMain sources
Carbon dioxideburning coal, oil, gas; deforestation
Methanepaddy fields, cattle, landfills
Nitrous oxidechemical fertilisers
Fluorinated gasesrefrigerators, air conditioners

5.4 National Action Plan on Climate Change (NAPCC), 2008

India launched the NAPCC in 2008 with eight national missions:

No.MissionFocus
1National Solar Missionsolar energy
2National Mission for Enhanced Energy Efficiencysaving energy in industry and homes
3National Mission on Sustainable Habitatgreen cities, waste, public transport
4National Water Missionwater conservation and efficiency
5National Mission for Sustaining the Himalayan Ecosystemprotecting the Himalayas
6National Mission for a Green Indiaafforestation
7National Mission for Sustainable Agricultureclimate-resilient farming
8National Mission on Strategic Knowledge for Climate Changeresearch

5.5 Importance of green jobs and green skills

Without and with green jobs
Without
  • more pollution
  • resources run out
  • health problems
  • climate disasters
VS
With
  • cleaner air and water
  • resources saved for the future
  • new employment
  • resilient communities
  • They create employment in new industries (solar, EVs, recycling).
  • They reduce costs through energy and water savings.
  • They support India's climate targets such as large renewable-energy capacity and net zero by 2070.
Green job story

In Rajasthan, women from self-help groups were trained as "Solar Mamas" to assemble and repair solar lanterns. Villages got clean light instead of kerosene, the women earned income, and smoke and CO2 emissions fell - economic, social and environmental benefits together.

5.6 Skills for green jobs

Skill typeExamples
Technicalinstalling solar panels, operating recycling machines, energy auditing
Knowledgeenvironmental laws, climate science basics
Soft skillsproblem solving, teamwork, awareness
Valuesresponsibility, care for nature

The Skill Council for Green Jobs (SCGJ) under Skill India trains youth for such roles.

5.6 Green jobs in India: examples

ProgrammeGreen jobs created
PM-KUSUMsolar pumps for farmers - installers, technicians
Rooftop solar (PM Surya Ghar)solar installers and maintenance staff
Swachh Bharat Missionwaste collectors, compost-plant operators
Electric mobilityEV assemblers, battery recyclers, charging-station staff
Namami Gangesewage-treatment plant operators
Green skill levels
Green experts - scientists and planners
Green technicians - installers and auditors
Green workers - collectors and operators
Green citizens - everyone

5.7 Exam-ready answers

Q. What are green jobs? Name any two sectors. (2 marks)

Green jobs are jobs that protect or restore the environment by saving energy and resources and reducing pollution. Sectors: renewable energy, organic agriculture, green transport, waste management.

Q. Explain any four benefits of green jobs. (4 marks)

They limit greenhouse-gas emissions; reduce waste and pollution; protect and restore ecosystems; use energy and raw materials efficiently; and help communities adapt to climate change, while also creating employment.

Quick revision: all five units at a glance

Ten marks: four one-mark questions (out of six) and three two-mark questions (out of five). One question comes from each unit, and two one-markers from Self-Management.

Unit 1: Communication Skills

Receiving>Understanding>Remembering>Evaluating>Responding
RESPECT for active listening
  • Remove distractions
  • Eye contact
  • Show you are listening
  • Pay attention
  • Empathise
  • Clarify doubts
  • Tune yourself to the speaker
Grammar to remember
  • Parts of speech: noun, pronoun, verb, adjective, adverb, preposition, conjunction, interjection
  • Active voice: Ravi wrote a letter. Passive voice: A letter was written by Ravi.
  • Capitals: MINTS: Months, I, Names, Titles, Starting letter

Unit 2: Self-Management Skills

TopicPoints
MotivationIntrinsic: for your own joy. Extrinsic: for reward or praise.
Result orientationset clear goals, make an action plan, use the right tools, work in the given time
Big Five personality factorsOpenness, Conscientiousness, Extraversion, Agreeableness, Neuroticism
Personality disordersCluster A (suspicious): paranoid, schizoid, schizotypal. Cluster B (emotional, impulsive): antisocial, borderline, histrionic, narcissistic. Cluster C (anxious): avoidant, dependent, obsessive-compulsive.

Unit 3: ICT Skills

TopicPoints
Spreadsheetrows, columns, cells (B5); formula begins with =; functions SUM, AVERAGE, MAX, MIN, COUNT
Sort and filtersort arranges the rows; filter shows only the rows that meet a condition
Protectiona password stops others from opening or changing the sheet
Presentationslides with text, pictures, charts, animation; F5 starts the slide show
ProgramsLibreOffice Calc, MS Excel, Google Sheets; LibreOffice Impress, MS PowerPoint

Unit 4: Entrepreneurial Skills

Types of entrepreneurs

Service, business (trading), industrial, agricultural, technical, social

Competencies

Decisiveness, initiative, interpersonal skills, perseverance, organisational skills

Barriers
  • Environmental: raw material, labour, roads
  • No or faulty business plan
  • Personal: self-doubt, fear of failure
Attitudes

Takes risk, believes in self, open to ideas, sees a problem as an opportunity

Unit 5: Green Skills

TopicPoints
Green jobsjobs that protect or restore the environment
Fieldsagriculture (organic farming), transport (electric vehicles), water conservation, solar and wind energy, eco-tourism, green buildings, solid waste management, appropriate technology
Benefitslimit greenhouse gases, reduce waste and pollution, protect ecosystems, help in adapting to climate change
NAPCC 2008National Action Plan on Climate Change, with eight national missions
Greenhouse gasescarbon dioxide, methane, nitrous oxide, water vapour (oxygen is not one)

More in detail

Tap and learnPersonality: tap a factor or a cluster

The Big Five (OCEAN) and the three clusters of personality disorders.

Openness

High: curious, creative, likes new ideas

Low: prefers routine and familiar things

Conscientiousness

High: organised, careful, finishes work in time

Low: careless, postpones work

Extraversion

High: outgoing, talkative, energetic

Low: quiet, prefers to be alone (introvert)

Agreeableness

High: kind, helpful, cooperative

Low: competitive, less trusting

Neuroticism

High: anxious, gets upset easily

Low: calm, emotionally stable

Cluster A: suspicious

Disorders: paranoid (distrusts others), schizoid (stays alone), schizotypal (odd beliefs)

Cluster B: emotional and impulsive

Disorders: antisocial (ignores rules), borderline (unstable moods), histrionic (seeks attention), narcissistic (feels superior)

Cluster C: anxious

Disorders: avoidant (fears criticism), dependent (cannot decide alone), obsessive-compulsive (wants perfect order)

Four types of sentences

TypeWhat it doesExample
Statement (declarative)gives informationThe exam begins at ten.
Question (interrogative)asks somethingWhen does the exam begin?
Emotion (exclamatory)shows a strong feelingWhat a wonderful result!
Order (imperative)gives a command or requestPlease open your books.

Spreadsheet functions

FormulaResult if A1 = 20, A2 = 30, A3 = 50
=SUM(A1:A3)100
=AVERAGE(A1:A3)33.33
=MAX(A1:A3)50
=MIN(A1:A3)20
=COUNT(A1:A3)3

GameStages of active listening

Tap the five stages in the right order, from first to last.

GameWhich cluster is it?

Read the personality disorder and tap its cluster.

Open its questions
4

Unit 2: Data science methodology

8 marks · five one-markers, one short and one long question

Tap and learnThe ten steps, with one running example

Example project: a school wants to reduce the number of students who fail in Class XI.

Step 1: Business Understanding

Asks: What is the problem that you are trying to solve?

Work: Meet the people concerned and write a clear goal.

In the example: Goal: find the students at risk of failing by October, so that they can be helped.

Step 2: Analytic Approach

Asks: How can you use data to answer the question?

Work: Choose descriptive, diagnostic, predictive or prescriptive analytics.

In the example: Predictive: classify each student as "at risk" or "safe".

Step 3: Data Requirements

Asks: What data do you need?

Work: List the data, its format and its sources.

In the example: Attendance, unit-test marks, homework record, of the last three years.

Step 4: Data Collection

Asks: Where is the data coming from and how will you get it?

Work: Gather the data and look for gaps.

In the example: Export marks and attendance from the school software as CSV files.

Step 5: Data Understanding

Asks: Is the data representative of the problem?

Work: Use statistics and charts to check quality and patterns.

In the example: A chart shows that attendance of one section is missing for a month.

Step 6: Data Preparation

Asks: What work is needed to clean and shape the data?

Work: Remove errors, fill missing values, combine tables, create new features. It takes the most time.

In the example: Make a new feature "average of three unit tests" (feature engineering).

Step 7: Modelling

Asks: How can the data be modelled to get the answer?

Work: Build descriptive or predictive models on the training set.

In the example: Train a classification model on the data of 80% of the students.

Step 8: Evaluation

Asks: Does the model really answer the question?

Work: Test on unseen data: diagnostic measures and statistical significance.

In the example: On the other 20%, check accuracy, precision and recall. Recall matters: no weak student should be missed.

Step 9: Deployment

Asks: Can you put the model into practice?

Work: Make the model available to the users.

In the example: Class teachers get a list of at-risk students every month.

Step 10: Feedback

Asks: Can you get constructive feedback?

Work: Collect results from real use and refine the model. The cycle repeats.

In the example: Teachers report students wrongly marked; the model is retrained.

2.1 What is data science methodology?

Data science is the field of extracting useful knowledge and insights from data using statistics, programming and domain knowledge. A data science methodology is a step-by-step framework that guides a team from a business question to a working solution. The CBSE syllabus follows John Rollins' (IBM) Foundational Methodology for Data Science, which has 10 stages.

IBM data science methodology
1Business understanding
➜
2Analytic approach
➜
3Data requirements
➜
4Data collection
➜
5Data understanding
➜
6Data preparation
➜
7Modelling
➜
8Evaluation
➜
9Deployment
➜
10Feedback
↻ back to step 1 — it is a cycle

The ten stages answer ten questions:

No.StageQuestion answered
1Business understandingWhat is the problem we are trying to solve?
2Analytic approachHow can we use data to answer the question?
3Data requirementsWhat data do we need?
4Data collectionWhere does the data come from and how do we get it?
5Data understandingIs the data representative of the problem?
6Data preparationWhat extra work is needed to make the data usable?
7ModellingHow can we visualise / model the data to get the answer?
8EvaluationDoes the model really answer the question?
9DeploymentCan we put the model into practice?
10FeedbackCan we get feedback to improve it?

2.2 Stage by stage with an example

Running example: hospital readmissions

A hospital wants to reduce the number of patients who are readmitted within 30 days of discharge.

StageWhat the team does in the example
Business understandingmeets doctors and managers; goal: predict patients at high risk of readmission
Analytic approachthe answer is yes/no -> classification (a decision tree, for example)
Data requirementsage, diagnosis, previous admissions, medicines, length of stay, follow-up visits
Data collectionrecords from the hospital database; fill gaps from pharmacy and lab systems
Data understandingdescriptive statistics, histograms, correlation; check missing values
Data preparationclean, remove duplicates, fill missing values, create features (e.g. number of visits last year) - often 70-90% of the project time
Modellingtrain decision-tree models on training data; tune parameters
Evaluationtest on unseen data; check accuracy, precision, recall; discuss with doctors
Deploymentthe model runs inside the hospital system and flags high-risk patients
Feedbackreadmission rates are monitored; the model is retrained with new data

Types of analytic approach

Analytic approaches
📋
Descriptive

what happened? summaries, dashboards

🔍
Diagnostic

why did it happen? statistical analysis

🔮
Predictive

what will happen? classification / regression

🧭
Prescriptive

what should we do? optimisation, recommendations

2.3 Data understanding and preparation in detail

TaskExample
Univariate statisticsmean age 54, standard deviation 12
Pairwise correlationlength of stay strongly correlated with readmission
Missing values8% of "blood pressure" values missing -> fill with median
Invalid valuesage = 250 -> treat as error
Feature engineeringcombine height and weight into BMI
Encoding"Yes / No" -> 1 / 0

2.4 Model validation

To know whether a model will work on new data, we test it on data it has not seen.

Train-test split

The data is divided, for example, 80% training and 20% testing. The model learns from training data; the test score estimates real performance.

K-fold cross-validation

5-fold cross-validation
1Split data into 5 equal folds
➜
2Train on 4 folds, test on the 5th
➜
3Repeat 5 times, each fold tested once
➜
4Average the 5 scores

Cross-validation uses all data for both training and testing and gives a more reliable estimate, especially with small datasets.

Train-test split vs K-fold
Train-test split
  • one split
  • fast
  • result depends on which rows land in the test set
VS
K-fold
  • K splits
  • slower
  • more reliable average score

2.5 Evaluation metrics

For regression (numbers)

MSEMean Squared Error = average of (actual - predicted)^2
RMSERoot Mean Squared Error = square root of MSE (same unit as the data)
MAEMean Absolute Error = average of |actual - predicted|
Calculating MSE and RMSE

Actual sales: 10, 12, 15; predicted: 11, 12, 13. Errors: -1, 0, 2. Squared: 1, 0, 4. MSE = 5 / 3 = 1.67. RMSE = square root of 1.67 = 1.29. MAE = (1 + 0 + 2) / 3 = 1.

actual = [10, 12, 15]; pred = [11, 12, 13]
err = [a - p for a, p in zip(actual, pred)]
mse = sum(e * e for e in err) / len(err)
print("MSE", round(mse, 2), "RMSE", round(mse ** 0.5, 2), "MAE", sum(abs(e) for e in err) / len(err))

For classification (classes)

MetricFormula
Accuracy(TP + TN) / total
PrecisionTP / (TP + FP)
RecallTP / (TP + FN)
F1 score2PR / (P + R)

2.6 Exam-ready answers

Q. Name the stages of the data science methodology in order. (2 marks)

Business understanding, analytic approach, data requirements, data collection, data understanding, data preparation, modelling, evaluation, deployment and feedback.

Q. Explain K-fold cross-validation. Why is it better than a single train-test split? (4 marks)

The data is divided into K equal folds. The model is trained on K - 1 folds and tested on the remaining fold; this is repeated K times so that each fold is the test set once, and the K scores are averaged. It uses all the data for both training and testing and gives a more reliable, less luck-dependent estimate than one split.

Quick revision: one-look summary

The Data Science Methodology, given by John Rollins of IBM, is a set of 10 steps that takes a project from the problem to the solution and back for improvement.

No.StepQuestion it answers
1Business UnderstandingWhat is the problem that you are trying to solve?
2Analytic ApproachHow can you use data to answer the question?
3Data RequirementsWhat data do you need to answer the question?
4Data CollectionWhere is the data coming from and how will you get it?
5Data UnderstandingIs the data that you collected representative of the problem?
6Data PreparationWhat additional work is required to clean and shape the data?
7ModellingIn what way can the data be visualised or modelled to get the answer?
8EvaluationDoes the model really answer the initial question?
9DeploymentCan you put the model into practice?
10FeedbackCan you get constructive feedback from the users?

Four analytic approaches

  • Descriptive: what happened?
  • Diagnostic: why did it happen?
  • Predictive: what will happen?
  • Prescriptive: what should be done?

Words to remember

  • Feature engineering: making new useful features from raw data, in Data Preparation
  • Descriptive model: shows patterns of the past. Predictive model: forecasts the future
  • Evaluation phases: diagnostic measures, statistical significance

Model validation

Train-test split

The data is divided once: about 80% to train, 20% to test.

Quick, but depends on which records fall in the test set.
k-fold cross validation

The data is divided into k folds. The model is trained k times; each fold is the test set once.

More reliable, takes more time. 5-fold on 1,000 records: each fold has 200.

Metrics for classification: the confusion matrix

Confusion matrix

Reality: YesReality: No
Predicted: Yes40TP10FP
Predicted: No5FN45TN

Read it like this

  • TP: predicted Yes, really Yes
  • TN: predicted No, really No
  • FP: predicted Yes, really No
  • FN: predicted No, really Yes
MetricFormulaWith TP = 40, FP = 10, FN = 5, TN = 45
Accuracy(TP + TN) / Total(40 + 45) / 100 = 85 / 100 = 0.85 (85%)
PrecisionTP / (TP + FP)40 / (40 + 10) = 40 / 50 = 0.80 (80%)
RecallTP / (TP + FN)40 / (40 + 5) = 40 / 45 = 0.89 (88.9%)
F1 score2 x Precision x Recall / (Precision + Recall)2 x 0.80 x 0.89 / (0.80 + 0.89) = 1.4222 / 1.69 = 0.84

Metrics for regression: MSE and RMSE

CaseActualPredictedErrorSquared error
1504824
26064-416
3706824
48084-416
MSE  = sum of squared errors / number of cases = (4 + 16 + 4 + 16) / 4 = 40 / 4 = 10
RMSE = square root of MSE = 3.16

MSE can never be negative, because every error is squared.
A smaller MSE or RMSE means a better model.

Try it Confusion matrix calculator

Try it MSE and RMSE calculator

More in detail

Four analytic approaches

Analytic approachQuestionExampleTechnique
DescriptiveWhat happened?Result of last year, class-wisesummary statistics, charts
DiagnosticWhy did it happen?Why did Class XI results fall?drill-down, correlation
PredictiveWhat will happen?Which students may fail this year?classification, regression
PrescriptiveWhat should be done?Which remedial plan will help most?optimisation, recommendation

Four model validation techniques

TechniqueHow it worksRemember
Train-test splitthe data is divided once, such as 80% to train and 20% to testquick; the result depends on which records fall in the test set
K-fold cross validationthe data is cut into k folds; each fold is the test set once; the k scores are averagedmore reliable; takes k times the work
Leave-one-out cross validationeach single record is the test set once; the model is trained on all the othersfor small data; very slow for large data
Time series cross validationthe model is trained on earlier periods and tested on later onesfor data in time order, such as monthly sales; the order is never shuffled

Five-fold cross validation in a picture

The data is cut into five equal folds. In every round a different fold is the test set. The five scores are averaged.

Which metric to use

Which metric?Use it whenExample
Accuracythe classes are balancedcat or dog photos, half each
Precisiona False Positive is costlyspam filter: genuine mail must not be lost
Recalla False Negative is costlydisease test: no patient should be missed
F1 scoreboth matter, or the classes are unequalfraud detection
MAE, MSE, RMSEthe model predicts a number (regression)price of a house, marks

Three metrics for regression, on the same four errors: 2, -4, 2, -4

MetricHow it is foundValue
MAE
Mean Absolute Error
mean of the errors without their signs: (2 + 4 + 2 + 4) / 43
MSE
Mean Squared Error
mean of the squared errors: (4 + 16 + 4 + 16) / 410
RMSE
Root Mean Squared Error
square root of MSE3.16

GamePut the ten steps in order

Tap the steps of the Data Science Methodology from first to last.

GameWhich analytic approach?

Read the question that the data must answer and tap the approach.

Open its questions
5

Unit 3: Making machines see

6 marks · five one-markers and one short question

Tap and learnThe five stages, with one running example

Example: a toll plaza camera that reads the number plate of a car.

Stage 1: Image acquisition

Work: Capture the scene as a digital image or video.

Devices: digital camera, scanner, design software.

In the example: The camera takes a photo of the car as it reaches the booth.

Stage 2: Preprocessing

Work: Improve the image and make it uniform.

Techniques: noise reduction, normalisation, resizing and cropping, histogram equalisation.

In the example: Night-time grain is removed, contrast is improved and the photo is cropped to the car.

Stage 3: Feature extraction

Work: Find the important visual patterns.

Techniques: edge detection, corner detection, texture analysis, colour-based features.

In the example: Edges show the rectangle of the plate and the outline of each character.

Stage 4: Detection / Segmentation

Work: Find and separate the objects or regions of interest.

Tasks: classification, localisation, object detection, semantic and instance segmentation.

In the example: The plate is located and each letter and digit is separated from the background.

Stage 5: High-level processing

Work: Interpret the result and take a decision.

Tasks: recognising objects, understanding the scene, analysing the context.

In the example: The characters are read as DL 8C AB 1234 and the toll is charged to that vehicle.

3.1 Computer vision

Computer vision (CV) is the field of AI that enables machines to see, process, analyse and understand images and videos and take actions based on them. Humans see with eyes and understand with the brain; machines "see" with cameras and "understand" with algorithms.

Human vision vs computer vision
Human
  • eyes capture light
  • brain recognises instantly
  • uses experience and context
  • tires easily
VS
Computer
  • camera captures pixels
  • algorithms find patterns
  • learns from many labelled images
  • works 24x7 at large scale

3.2 How machines see: pixels

A digital image is a grid of pixels. Each pixel stores numbers:

Image typeValues per pixelRange
Binary10 (black) or 1 (white)
Grayscale10 (black) to 255 (white)
Colour (RGB)3 (Red, Green, Blue)each 0 to 255
Size of an image

A 1920 x 1080 colour image has 1920 x 1080 = 2,073,600 pixels. With 3 bytes per pixel it needs about 6.2 MB before compression.

3.3 The computer vision process

CV pipeline
1Image acquisition
➜
2Pre-processing
➜
3Feature extraction
➜
4Detection / segmentation
➜
5High-level processing and decision
StageWhat happensExample: number-plate reading
Image acquisitioncapture images via cameras, scanners, satellitestoll camera captures the car
Pre-processingresize, remove noise, adjust brightness and contrast, convert to grayscalethe image is cleaned and enhanced
Feature extractionfind edges, corners, shapes, textures, coloursplate edges and characters located
Detection / segmentationfind and separate the objects of interestthe plate region is cut out
High-level processingrecognise, classify and decidecharacters read: DL 3C AB 1234; toll charged

3.4 Computer vision tasks

CV tasks
🏷️
Image classification

one label for the whole image

📦
Object detection

boxes and labels for many objects

✂️
Image segmentation

label every pixel (semantic / instance)

🧑
Face recognition

identify or verify a person

🔤
OCR

read printed or handwritten text

🎞️
Object tracking

follow objects across video frames

🕺
Pose estimation

find body joints

3.5 Features and convolution

Features are distinctive parts of an image: edges, corners, blobs, textures. CNNs learn them using convolution - sliding a small kernel (filter) over the image, multiplying and adding values to create a feature map.

CNN layers
1Input image
➜
2Convolution - detect features
➜
3ReLU - keep positive values
➜
4Pooling - reduce size
➜
5Fully connected - classify
➜
6Output probabilities

3.6 Applications

FieldApplication
Healthcaredetecting tumours, diabetic retinopathy, fractures
Agriculturecrop-disease detection, weed spraying robots
Transportself-driving cars, traffic monitoring, ANPR at tolls
Retailcashier-less stores, shelf monitoring
SecurityCCTV analysis, intrusion detection
Manufacturingdefect detection on assembly lines
GovernanceDigiYatra face boarding at airports

3.7 Challenges of computer vision

Challenges
Computer vision
Lighting changes
Occlusion - objects hidden
Different viewpoints and scale
Cluttered backgrounds
Huge labelled data needed
Privacy concerns
Bias in datasets

3.8 Ethics in computer vision

  • Privacy: face recognition in public spaces raises surveillance concerns; consent is required.
  • Bias: unequal accuracy across skin tones, ages and genders.
  • Deepfakes: manipulated videos can spread misinformation.
  • Accountability: who is responsible when a self-driving car errs?

3.9 No-code and low-code CV

Teachable Machine (Google) lets you train an image classifier in the browser: collect images for each class, train, test and export. OpenCV is the popular open-source library for CV in Python.

Below is the same idea in plain Python on a tiny 5 x 5 image, so you can run it here. (With OpenCV on your computer the steps are cv2.imread, cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) and cv2.Canny.)

# a tiny 5 x 5 colour image: each pixel is (R, G, B)
W, B = (250, 250, 250), (20, 20, 20)
img = [[W, W, W, W, W],
       [W, B, B, B, W],
       [W, B, B, B, W],
       [W, B, B, B, W],
       [W, W, W, W, W]]
# 1. grayscale: gray = 0.299 R + 0.587 G + 0.114 B
gray = [[round(0.299 * r + 0.587 * g + 0.114 * b) for (r, g, b) in row] for row in img]
for row in gray: print(row)
# 2. vertical-edge detection with the kernel [-1, 0, 1] on each row
print("Edges:")
for row in gray:
    print([abs(row[c + 1] - row[c - 1]) for c in range(1, 4)])

3.10 Exam-ready answers

Q. Name the stages of the computer vision process. (2 marks)

Image acquisition, pre-processing, feature extraction, detection/segmentation, and high-level processing (recognition and decision).

Q. Explain any four applications of computer vision. (4 marks)

Medical imaging - detecting tumours and fractures; self-driving cars - detecting lanes and pedestrians; number-plate recognition at toll plazas; agriculture - detecting crop disease from leaf images; manufacturing - finding defects on assembly lines.

Quick revision: one-look summary

Computer vision (machine vision) lets a machine see, process and understand images and videos. An image is a grid of pixels; each pixel of an 8-bit grayscale image is a number from 0 (black) to 255 (white), and a colour pixel has three such numbers (red, green, blue).

Picture: an image is a grid of numbers

black0
64
grey128
192
white255

Resolution = width x height. A 640 x 480 image has 3,07,200 pixels: 3,07,200 bytes in grayscale and 9,21,600 bytes in RGB.

The computer vision process: five stages

Image acquisition>Preprocessing>Feature extraction>Detection / Segmentation>High-level processing
StageWorkTechniques or examples
Image acquisitioncapture the image in digital formcamera, scanner, satellite, medical sensor
Preprocessingimprove and standardise the imagenoise reduction, normalisation, resizing or cropping, histogram equalisation
Feature extractionfind the important visual patternsedge detection, corner detection, texture analysis, colour-based features
Detection / Segmentationfind the objects or regionsclassification, localisation, object detection, semantic and instance segmentation
High-level processinginterpret and deciderecognise a face, read a number plate, understand the scene

Tasks on one object and on many objects

Image classification
cat
One label for the whole image: "cat".
Classification + localisation
cat
The label and a box for the single object.
Object detection
catdog
Many objects: a box and a label for each.
Instance segmentation
cat 1cat 2
The exact outline (pixels) of every object.

Applications

  • Facial recognition and biometrics (face unlock, fingerprint)
  • Health care: tumours in X-ray and MRI
  • Self-driving vehicles: lanes, people, signs
  • Optical character recognition (OCR): reading printed text
  • Machine inspection, 3D model building, surveillance

Challenges

  • Reasoning and analytical issues
  • Difficulty in image acquisition: light, angle, hidden objects
  • Privacy and security
  • Duplicate and false content (deepfakes)

More in detail

Try it Binary art: a picture made of 0s and 1s

Tap the squares to draw. The computer stores your picture as the numbers on the right: 1 for a white pixel, 0 for a black pixel.

Try it RGB colour mixer

Every colour pixel has three numbers: red, green and blue. Move the sliders or tap a colour.

Techniques and their stage

TechniqueStageWhat it does
Noise reductionPreprocessingremoves grain and speckles
NormalisationPreprocessingbrings pixel values to a common range, such as 0 to 1
Resizing, croppingPreprocessingmakes all images the same size; removes unwanted parts
Histogram equalisationPreprocessingimproves the contrast of a dull image
Edge detectionFeature extractionfinds the boundaries where brightness changes sharply
Corner detectionFeature extractionfinds points where two edges meet
Texture analysisFeature extractiondescribes the surface pattern: smooth, rough, striped
Colour-based featuresFeature extractionuses the colours of an object to tell it apart

One object or many objects

One objectMany objects
What is it?Image classificationObject detection
Where is it?Classification + localisation (one box)Object detection (a box for each)
Exact shape?-Semantic segmentation (by class), instance segmentation (each object)

Eight applications of computer vision

ApplicationWhat the machine does
Facial recognitionunlocks a phone, marks attendance by face
Health carefinds tumours and fractures in X-ray, CT and MRI images
Self-driving vehiclessees lanes, signals, vehicles and people on the road
Optical character recognition (OCR)reads printed or written text from an image, such as a number plate
Machine inspectionfinds faulty products on a factory line
3D model buildingbuilds a 3D model of an object or place from photos
Surveillancewatches CCTV video for unusual activity
Fingerprint recognition and biometricschecks the identity of a person

Four challenges

  • Reasoning and analytical issues: the machine sees pixels; understanding the meaning of a scene is hard
  • Difficulty in image acquisition: poor light, odd angles, hidden or moving objects
  • Privacy and security concerns: faces and places are recorded and stored
  • Duplicate and false content: fake and edited images and videos (deepfakes)

The future of computer vision

  • Systems now read visual data with near-human precision, because of deep learning and large labelled data
  • Expected: personalised health-care diagnosis and immersive augmented reality (AR)
  • Progress needs teamwork and attention to ethics

GamePut the five stages in order

Tap the stages of the computer vision process from first to last.

GameWhich stage is it?

Read the work and tap the stage of computer vision.

Open its questions
6

Unit 5: Big data and data analytics

6 marks · three one-markers, one short and one long question

Tap and learnThe six Vs, with one running example

Example: an online shopping site during a festival sale.

Velocity: how fast

Meaning: The speed at which data is produced, delivered and analysed.

In the example: Thousands of orders and payments arrive every second.

Volume: how much

Meaning: The huge amount of data.

In the example: Crores of product views, orders and reviews are stored.

Variety: how many kinds

Meaning: Structured, semi-structured and unstructured data together.

In the example: Order tables, JSON logs of clicks, product photos and video reviews.

Veracity: how trustworthy

Meaning: The consistency, accuracy, quality and trustworthiness of the data.

In the example: Fake reviews and duplicate accounts must be found and removed.

Value: how useful

Meaning: The benefit that the data gives to the organisation.

In the example: Recommendations made from the data increase the sales.

Variability: how changing

Meaning: The flow of data is not regular; it changes with time and situation, and still has to be dependable.

In the example: Traffic is ten times higher at midnight when the sale opens.

5.1 What is big data?

Big data refers to datasets that are so large, fast or varied that traditional tools (like a single spreadsheet or database) cannot store and process them efficiently. Social media posts, UPI transactions, sensor readings and satellite images create big data every second.

Where big data comes from
📱
Social media

posts, likes, videos

💳
Transactions

UPI, card payments, online shopping

📡
Sensors and IoT

smart meters, wearables, vehicles

🛰️
Satellites

weather and earth images

🏥
Healthcare

records, scans, genomes

🌐
Web logs

clicks and searches

5.2 Characteristics: the Vs of big data

The Vs
Big data
Volume - huge size
Velocity - high speed
Variety - many forms
Veracity - trustworthiness
Value - useful insight
Variability - changing meaning
VMeaningExample
Volumeenormous amount of databillions of UPI transactions a month
Velocityspeed of generation and processingstock prices change every millisecond
Varietystructured, semi-structured, unstructuredtables, JSON, videos, tweets
Veracityaccuracy and reliabilityfake reviews, sensor errors
Valueusefulness for decisionspredicting customer needs
Variabilitymeaning or flow changes"sick" can mean ill or awesome

5.3 Types of big data

Structured vs unstructured
Structured
  • fixed rows and columns
  • easy to search with SQL
  • e.g. bank records, marks table
VS
Unstructured
  • no fixed format
  • needs special tools
  • e.g. images, videos, e-mails, social posts

Semi-structured data has some organisation but not a fixed table: JSON, XML, e-mails (headers + free text). About 80% of the world's data is unstructured.

5.4 Big data analytics

Big data analytics is the process of examining large and varied data to find patterns, trends, correlations and insights for better decisions.

Types of analytics (more value at the top)
Prescriptive - what should we do?
Predictive - what will happen?
Diagnostic - why did it happen?
Descriptive - what happened?
TypeQuestionExample
DescriptiveWhat happened?last month's sales report
DiagnosticWhy did it happen?sales fell because of a competitor's discount
PredictiveWhat will happen?demand will rise during Diwali
PrescriptiveWhat should we do?stock 30% more sweets and offer combos
Working of big data analytics
1Collect data
➜
2Store (data lake / warehouse)
➜
3Process and clean
➜
4Analyse (statistics, ML)
➜
5Visualise and act

5.5 Tools and technologies

ToolUse
Hadoop (HDFS + MapReduce)distributed storage and batch processing on clusters
Apache Sparkfast in-memory processing, ML (MLlib), streaming
NoSQL databases (MongoDB, Cassandra)flexible storage for semi/unstructured data
Apache Kafkahandling real-time data streams
Tableau, Power BIvisualisation and dashboards
Python (Pandas, PySpark)analysis and ML
MapReduce idea: counting words

Map: each computer counts words in its part of the books - ("AI", 1), ("data", 1)... Shuffle: same words are grouped together. Reduce: counts are added - ("AI", 5,240). Many machines working in parallel finish a huge job quickly.

5.6 Mining data streams

A data stream is a continuous, fast flow of data (sensor readings, live tweets, transactions). Data stream mining analyses it in real time, often with one pass and limited memory, using techniques like sliding windows and sampling. Uses: fraud detection during a card swipe, live traffic updates, network intrusion detection.

5.7 Applications, benefits and challenges

Applications
🏦
Banking

real-time fraud detection

🛒
Retail

recommendations, pricing

🏥
Health

disease outbreak tracking

🚦
Smart cities

traffic and energy management

🌾
Agriculture

yield and weather prediction

🎬
Entertainment

personalised content (OTT)

BenefitsChallenges
better and faster decisionsstorage and processing cost
personalised servicesdata quality (veracity)
cost savings, efficiencyprivacy and security
new products and innovationshortage of skilled people

5.8 Exam-ready answers

Q. Explain any four Vs of big data. (2 marks)

Volume - huge size; Velocity - high speed of generation; Variety - different formats; Veracity - reliability of data. (Value and variability may also be written.)

Q. Explain the four types of big data analytics with examples. (4 marks)

Descriptive - what happened (monthly sales report); Diagnostic - why it happened (sales fell due to competition); Predictive - what will happen (forecasting festival demand); Prescriptive - what action to take (increase stock and offer discounts).

Quick revision: one-look summary

Big Data is data that is too large, too fast and too varied for traditional tools. Big Data analytics examines it to find patterns that help in decisions.

Three types of data

Structured

Fixed rows and columns.

SQL table, Excel sheet, transaction records
Semi-structured

Tags or keys, no fixed table.

XML, JSON, CSV and HTML files
Unstructured

No fixed format.

Images, videos, audio (MP3), e-mails, PDFs, social media posts

The CBSE handbook counts CSV files as semi-structured and e-mails as unstructured.

The six Vs

VMeaningExample
Volumehuge amount of datamillions of posts every day
Velocityspeed of producing and processinglive sensor data, stock prices
Varietydifferent types of datatext, images, audio, video
Veracitytrustworthiness and qualityfake reviews reduce veracity
Valueusefulness for the organisationoffers that increase sales
Variabilitythe flow of data is not regular; it changes with time and situationtraffic that rises suddenly during a sale

Working of Big Data analytics

1. Gather data>2. Process data>3. Clean data>4. Analyse data

Advantages

  • Enhanced decision making
  • Improved efficiency and productivity
  • Better customer insights
  • Competitive advantage
  • Innovation and growth

Disadvantages

  • Privacy and security concerns
  • Data quality issues
  • Technical complexity
  • Regulatory compliance
  • High cost and resources

Tools

Tableau, Apache Hadoop, Cassandra, MongoDB, SAS

Apache Spark and Power BI are also used. MySQL is a database, not an analytics tool.

Units of data

KB, MB, GB, TB, PB, EB, ZB

Each is 1,024 times the one before it.

Mining data streams: finding patterns and trends in data that flows continuously, in real time, as it arrives and without storing all of it first. Example: noticing a sudden rise in searches for "election results". Future of Big Data analytics: real-time analytics, more advanced models in predictive analytics, quantum computing.

More in detail

KB>MB>GB>TB>PB>EB>ZB

Each unit is 1,024 times the one before it: 1 TB = 1,024 GB. Big Data is measured in terabytes, petabytes, exabytes and zettabytes.

Traditional data and Big Data

Traditional dataBig Data
Sizemegabytes to gigabytesterabytes, petabytes and more
Typemostly structuredstructured, semi-structured and unstructured
Speedproduced slowly, in batchesproduced every second, as streams
Storageone server, relational databasemany computers together (distributed)
ToolsMySQL, spreadsheetsHadoop, Cassandra, MongoDB, Tableau, SAS

Working of Big Data analytics: four steps

StepWhat happensIn a hospital
1. Gather datacollect structured and unstructured data from cloud storage, mobile apps, IoT sensorspatient records, lab reports, scans, wearable devices
2. Process dataorganise the data, by batch processing or stream processingbring all the records of a patient together
3. Clean datacorrect the format; remove duplicate, irrelevant and wrong datacorrect wrong entries, merge duplicate patient IDs
4. Analyse datadata mining, predictive analytics, deep learningpredict which patients may need the ICU

Two ways to process the data

Batch processingStream processing
Howlarge blocks of data are processed together, over timesmall batches are processed as soon as they arrive
Delaylongervery short
Examplemonthly electricity billsalert for a doubtful card payment

GamePut the four steps in order

Tap the steps of Big Data analytics from first to last.

GameWhich V is it?

Read the line and tap the V of Big Data that it shows.

GameStructured, semi-structured or unstructured?

Read the data and tap its type.

Open its questions
7

Unit 6: Understanding neural networks

8 marks · five one-markers, one short and one long question

Tap and learnHow a network learns: four steps that repeat

Example: a network that predicts the marks of a student from study hours.

Step 1: Forward propagation

Work: The input passes through the layers. Each neuron finds (inputs x weights) + bias and applies the activation function.

In the example: For 5 study hours, the network predicts 60 marks.

Step 2: Calculate the loss

Work: The loss function compares the prediction with the actual value.

In the example: Actual marks are 70. Error = 10, squared error = 100.

Step 3: Backpropagation

Work: The error is sent backwards, to find how much each weight added to it.

In the example: The weight on "study hours" is found to be too small.

Step 4: Update the weights

Work: Gradient descent changes each weight and bias by a small step (learning rate) to reduce the loss.

In the example: The weight is increased a little; next time the prediction is 64. One pass over all the data is an epoch.

6.1 What is a neural network?

An artificial neural network (ANN) is a computing model inspired by the human brain. It is made of connected units called neurons (nodes) arranged in layers. Neural networks learn patterns from data and are the foundation of deep learning.

Biological vs artificial neuron
Biological neuron
  • dendrites receive signals
  • cell body processes
  • axon sends output
  • synapse strength changes with learning
VS
Artificial neuron
  • inputs (x) receive data
  • weighted sum + bias
  • activation function gives output
  • weights change with learning

6.2 Structure of a neural network

Layers of a neural network
1Input layer - receives features
➜
2Hidden layers - learn patterns
➜
3Output layer - gives the prediction
ComponentRole
Input layerone node per feature (e.g. pixels, age, income)
Hidden layersperform calculations and learn features; many hidden layers = deep network
Output layerfinal result: a class or a number
Weights (w)strength of each connection; learned during training
Bias (b)shifts the output; helps the model fit better
Activation functiondecides the neuron's output; adds non-linearity

6.3 How a neuron computes

Weighted sumz = (x1 x w1) + (x2 x w2) + ... + (xn x wn) + b; output = f(z)
Worked neuron

Inputs x1 = 2, x2 = 3; weights w1 = 0.5, w2 = -1; bias b = 1. z = 2 x 0.5 + 3 x (-1) + 1 = 1 - 3 + 1 = -1. With a step function (output 1 if z >= 0 else 0) the output is 0. With ReLU, output = max(0, -1) = 0. With sigmoid, output = 1 / (1 + e^1) = 0.27.

6.4 Activation functions

Common activation functions
📶
Step

0 or 1 - early perceptrons

〰️
Sigmoid

0 to 1 - probabilities

➖
Tanh

-1 to 1 - centred output

📐
ReLU

max(0, z) - fast; most used in hidden layers

🎲
Softmax

probabilities of many classes summing to 1

6.5 How a neural network learns

Training loop
1Forward propagation - make a prediction
➜
2Calculate the loss (error)
➜
3Backpropagation - find each weight's share of the error
➜
4Update weights (gradient descent)
➜
5Repeat for many epochs
↻ back to step 1 — it is a cycle
TermMeaning
Forward propagationinputs pass layer by layer to give an output
Loss functionmeasures error (e.g. MSE)
Backpropagationsends the error backward to compute how to change each weight
Gradient descentchanges weights a small step in the direction that reduces error
Learning ratesize of the step
Epochone full pass over the training data

6.6 The perceptron

The perceptron (Frank Rosenblatt, 1958) is the simplest neural network: a single neuron with a step activation. It can learn linearly separable problems like AND and OR, but not XOR - which needs hidden layers.

def perceptron(x1, x2, w1=1, w2=1, b=-1.5):
    z = x1 * w1 + x2 * w2 + b
    return 1 if z >= 0 else 0
for a in (0, 1):
    for c in (0, 1):
        print(a, c, "AND ->", perceptron(a, c))

6.7 Types of neural networks

TypeSpecial featureUsed for
Feed-forward (FFNN)data flows one way, input to outputtabular prediction
Convolutional (CNN)convolution and pooling layersimages, video
Recurrent (RNN / LSTM)loops that remember earlier inputstext, speech, time series
Generative adversarial (GAN)generator vs discriminatorcreating images
Transformersattention to all words at oncelanguage models (ChatGPT)

6.8 Impact, benefits and limitations

Neural networks
Benefits
  • learn complex patterns
  • work with images, sound, text
  • improve with more data
  • power modern AI
VS
Limitations
  • need huge data and computing
  • black box - hard to explain
  • can overfit
  • can be biased

6.9 Exam-ready answers

Q. What is the role of the activation function? Name two. (2 marks)

It decides the output of a neuron and adds non-linearity so the network can learn complex patterns. Examples: ReLU, sigmoid (also tanh, softmax).

Q. Explain how a neural network learns. (4 marks)

In forward propagation the inputs pass through the layers to give a prediction. The loss function measures the error. In backpropagation the error is sent backward to calculate how much each weight contributed. Gradient descent updates the weights to reduce the error. This repeats for many epochs until the error is small.

Quick revision: one-look summary

Picture: the layers

InputHidden 1Hidden 2Output
Input layer takes the data, hidden layers process it, output layer gives the answer.

In daily life: A relay race: the first runner takes the baton (input), the middle runners carry it (hidden), the last runner finishes (output).

Picture: how one neuron works

x1 = 1w1 = 3x2 = 0w2 = 5x3 = 1w3 = 1sum+ biasactivationsum >= 4 ?(1 x 3) + (0 x 5) + (1 x 1) + (-1) = 33 is less than 4, so the output is 0
Each input is multiplied by its weight; the products and the bias are added; the activation function decides the output.
ComponentMeaning
Neuronthe unit that receives inputs, processes them and gives an output
Weightthe strength (importance) of a connection
Biasan extra value added to the weighted sum
Activation functiondecides the output of a neuron; adds non-linearity: sigmoid (0 to 1), tanh (-1 to 1), ReLU (0 for negative, same for positive)
Forward propagationinput moves through the layers to give the output
Loss functionmeasures the error. Regression: MSE, MAE. Classification: binary cross-entropy (log loss)
Backpropagationthe error is sent back to adjust the weights and bias
Gradient descentchanges the weights step by step to reduce the loss

Types of neural networks

TypeIdeaUsed for
Standard NN (perceptron)single layeryes/no classification, such as spam detection
Feed-forward NN (FFNN)data moves in one direction through hidden layersimage recognition, NLP, regression
CNNconvolution filters find the features of an imageimage recognition, object detection, medical imaging
RNNloops that remember earlier inputstranslation, chatbots, speech recognition, time series
GANgenerator against discriminatorimage generation, style transfer, data augmentation

A network with two or more hidden layers is a deep neural network.

Try it Neuron calculator

More in detail

Try it Activation function explorer

Three activation functions

Input xSigmoidtanhReLU
-20.12-0.960
-10.27-0.760
00.500.000
10.730.761
20.880.962
ActivationRangeWhere used
Sigmoid0 to 1output layer for yes/no (probability)
tanh-1 to 1hidden layers; centred at zero
ReLU0 to any positive valuehidden layers of deep networks; fast

Which loss function

ProblemLoss function
Regression (predict a number)Mean Squared Error (MSE), Mean Absolute Error (MAE)
Two-class classificationBinary cross-entropy (log loss)
Many-class classificationCategorical cross-entropy

How one neuron works: five steps

  1. Each input is multiplied by its weight.
  2. The products are added.
  3. The bias is added.
  4. The activation function decides whether the neuron fires.
  5. The output is passed to the next layer (feed-forward).
One neuron, worked out

Inputs    x1 = 2    x2 = 3
Weights   w1 = 4    w2 = -1
Bias      b  = -2

Sum = (2 x 4) + (3 x -1) + (-2)
    = 8 - 3 - 2
    = 3

Step (threshold 4): 3 < 4, so 0
ReLU:    output 3
Sigmoid: output 0.95

More words of a neural network

WordMeaning
Connectionthe link between two neurons; it carries a weight
Learning rulethe method that adjusts the weights and bias; backpropagation is the common one
Learning ratethe size of each change in the weights; too large overshoots, too small is slow
Epochone complete pass of the whole training data through the network
Deep neural networka network with two or more hidden layers

Future of neural networks: good for society

  • Higher efficiency and productivity through automation
  • Personalised products and services
  • Economic growth and new kinds of jobs

Future of neural networks: concerns

  • Data privacy
  • Bias in the algorithm
  • Loss of some jobs (job displacement)

GameHow one neuron works: put the steps in order

Tap the five steps from first to last.

GameWhich neural network is it?

Read the line and tap the type of network.

Open its questions
8

Unit 7: Generative AI

7 marks · three one-markers, one short and one long question

Tap and learnFour kinds of content, with tools and a sample prompt

Tap a kind of content to see the tools and how to ask.

Text generation

Tools: ChatGPT, Gemini (Bard), Perplexity

Model: Large Language Model (LLM)

Sample prompt: "Explain Big Data to a Class XII student in 80 words with one example."

Image generation

Tools: Canva, DALL-E, Stable Diffusion

Use: posters, logos, pictures for a project

Sample prompt: "A poster of a robot teaching in a classroom, flat colours, blue and orange."

Video generation

Tools: Google Lumiere, Animaker

Use: short clips, animated explainers

Sample prompt: "A 10-second animation of the water cycle for school children."

Audio generation

Tools: Google MusicLM, Meta AI Voicebox

Use: background music, narration

Sample prompt: "A calm 30-second flute tune for a morning assembly."

7.1 What is generative AI?

Generative AI is AI that creates new content - text, images, audio, video, code and 3-D designs - by learning patterns from large datasets. Examples: ChatGPT, Gemini, Claude (text), DALL-E, Midjourney, Stable Diffusion (images), Suno (music), GitHub Copilot (code).

Generative vs discriminative models
Discriminative
  • learns the boundary between classes
  • answers "is it a cat or a dog?"
  • e.g. logistic regression, classifiers
VS
Generative
  • learns how data is formed
  • creates new samples
  • "draw a new cat"
  • e.g. GANs, VAEs, LLMs

7.2 How generative AI works

From data to new content
1Huge training data
➜
2Learn patterns (neural networks)
➜
3Take a prompt
➜
4Generate output step by step
➜
5Human review and feedback

7.3 Generative models

GAN - Generative Adversarial Network

GAN training
1Generator makes fake images from noise
➜
2Discriminator judges real or fake
➜
3Feedback to both
➜
4Generator improves until fakes look real
↻ back to step 1 — it is a cycle

VAE - Variational Autoencoder

An encoder compresses data into a small latent space; a decoder rebuilds data from it. Sampling new points in the latent space creates new, similar outputs.

Transformers and Large Language Models (LLMs)

A transformer (2017, "Attention is all you need") uses self-attention to look at all words in a sentence at once and decide which words relate to each other. LLMs are huge transformers trained on massive text to predict the next token. GPT stands for Generative Pre-trained Transformer.

Diffusion models

They learn to remove noise step by step; to generate, they start from random noise and gradually "denoise" it into an image matching the prompt.

ModelKey ideaExample tools
GANtwo networks competeStyleGAN faces
VAEencode - decode through latent spaceimage variation
Transformer / LLMattention, next-token predictionChatGPT, Gemini
Diffusionnoise to imageStable Diffusion, DALL-E 3

7.4 Prompt engineering

A prompt is the input instruction. Prompt engineering is the skill of writing prompts that produce useful, accurate output.

Elements of a good prompt
🎭
Role

"You are a Class XII biology teacher"

🎯
Task

"Explain photosynthesis"

📚
Context

"for students who find it hard"

📐
Format

"in 5 bullet points with one example"

🚧
Constraints

"under 120 words, simple English"

TechniqueExample
Zero-shot"Translate 'Good morning' into Tamil."
Few-shotgive 2 examples of the format, then ask for a third
Chain-of-thought"Solve step by step and show your working."
Iterative refinementimprove the prompt after seeing the answer

7.5 Applications

Uses of generative AI
Generative AI
Content writing and summaries
Image and design creation
Coding assistance
Personalised tutoring
Drug and material discovery
Music and video
Customer-support chatbots
Translation and accessibility

7.6 Limitations and risks

RiskMeaning
Hallucinationconfident but false information
Biasstereotypes from training data
Deepfakes and misinformationfake images, voices, videos
Copyright and ownershipwho owns AI-made content? training on others' work
Privacysensitive data entered in prompts
Over-dependenceloss of one's own skills
Environmental costlarge energy and water use

7.7 Responsible use

Use generative AI responsibly
1Check facts with reliable sources
➜
2Do not share personal data
➜
3Give credit; disclose AI use
➜
4Avoid harmful or fake content
➜
5Keep human judgement
Responsible use in a project

Riya uses an AI chatbot to brainstorm ideas for her capstone report, then reads three reliable sources, writes the report herself, cites the sources and mentions "AI used for brainstorming" in the acknowledgement. This is ethical use.

7.8 Hands-on ideas

  • Compare answers of two chatbots to the same prompt and check facts.
  • Use an image generator with a detailed prompt; note how changes in the prompt change the output.
  • Spot AI-generated images: odd hands, garbled text, inconsistent shadows.

7.9 Exam-ready answers

Q. Differentiate between generative and discriminative models. (2 marks)

Discriminative models learn to distinguish classes (e.g. spam or not). Generative models learn the data distribution and create new data (e.g. new images or text).

Q. What is hallucination in generative AI? How can users reduce its effect? (4 marks)

Hallucination is when a generative AI model gives confident but incorrect or made-up information. Users can reduce its effect by verifying facts from reliable sources, asking for sources, giving clear context in prompts, asking the model to say when it is unsure, and keeping human review before using the output.

Quick revision: one-look summary

Generative AI creates new content (text, images, audio, video) that resembles the data it was trained on.

Generative model

Learns how the data is distributed and makes new samples.

GAN, VAE, LLM, Naive Bayes
Discriminative model

Learns the boundary between classes and gives a label.

Logistic regression, decision tree, SVM, random forest

Picture: a GAN

NoiseGeneratorfakeReal datarealDiscriminatorrealorfake?feedback
The generator makes fakes; the discriminator catches them; both keep improving.

In daily life: A forger makes fake notes and a bank officer checks them. Each one gets better because of the other.

TypePartsIdea
GANgenerator, discriminatorthe generator makes samples; the discriminator judges real or fake; the two compete
VAEencoder, decoderthe encoder compresses data to a code (latent space); the decoder builds new data from the code
LLMa very large deep learning networktrained on huge text; generates language word by word

Applications and tools

ContentTools
TextChatGPT, Gemini (Bard), Perplexity
ImagesCanva, DALL-E, Stable Diffusion, Midjourney
VideoGoogle Lumiere, Animaker
AudioGoogle MusicLM, Meta AI Voicebox

Large Language Models (LLM)

What and where

  • Deep learning models trained on huge text to understand and generate language
  • Examples: GPT-4o, Gemini, LLaMA, Claude
  • Uses: writing text, stories and dialogue; writing code; translation; answering questions; captions for images and videos

Limitations and risks

  • Need very high processing power; answers take time
  • Fluent language comes before accuracy: confident but wrong answers (hallucination)
  • Bias from the training text
  • Privacy: confidential data may be revealed
  • Misuse: harmful output from tricky prompts, fake news

Ethical and social implications

Deepfakes

AI-made fake video, image or audio of a real person.

Bias and discrimination

Outputs repeat the bias of the training data.

Plagiarism and copyright

Passing off AI content as your own; using others' work without credit.

Transparency

People should be told when content is made by AI.

More in detail

Generative and discriminative models

Generative modelDiscriminative model
Aimcreate new dataclassify or label data
Learnshow the data is distributedthe boundary between classes
Outputnew text, image, audio, videoa class label or a score
Used inart and design, finding unusual patternsface and speech recognition, spam detection
ExamplesGAN, VAE, LLM, Naive Bayeslogistic regression, decision tree, SVM, random forest

GAN and VAE

GANVAE
Full formGenerative Adversarial NetworkVariational Autoencoder
Partsgenerator and discriminatorencoder and decoder
Ideatwo networks competecompress to a code (latent space), then rebuild
Outputsharp, realisticsmoother
Traininghardermore stable

Write a better prompt

Weak promptBetter promptWhy
Write about AIWrite five points on the uses of AI in farming for a school magazinegives the task, the length and the audience
Make a pictureDraw a green poster on "Save Water" with a tap and a drop, simple stylegives the subject, the colour and the style
Explain neural networkExplain a neural network with a daily-life example in 60 wordsgives the format and the limit

Future of generative AI

  • New model designs that go beyond what is possible today
  • Ethical development that reduces bias
  • More use in health care and education
  • Better language work, such as translation among many languages
  • More multimedia content creation
  • People and AI working together, with AI as a helper

Use generative AI responsibly

  • Check every fact from a reliable source
  • Say that AI was used; do not pass it off as your own work
  • Do not create or share fake images, audio or video of anyone
  • Do not type personal or secret data into a chatbot
Remember

In answers on ethics, name the issue first (deepfake, bias, plagiarism, transparency), then give one example and one safeguard.

GameGenerative or discriminative?

Read the task or the model and tap its kind.

GameWhich ethical issue is it?

Read the case and tap the issue.

Open its questions
9

Unit 8: Data storytelling

5 marks · three one-markers, one short and one long question

Tap and learnFreytag's Pyramid, with one running example

Example: a data story on school attendance.

Stage 1: Introduction

Work: Give the setting and introduce the characters and the question. It is also called the exposition.

In the example: The school records the attendance of 1,200 students every day. Is it the same on all days?

Stage 2: Rising action

Work: Show the events and facts that build towards the climax.

In the example: A line graph shows a dip in attendance every Monday.

Stage 3: Climax

Work: Give the main insight: the most intense point, the turning point of the story.

In the example: The dip is three times bigger for students who travel more than 10 km.

Stage 4: Falling action

Work: Show what follows from the insight, before the final outcome.

In the example: Monday unit tests are missed by these students, and their marks are lower.

Stage 5: Conclusion

Work: Resolve the problem and suggest the action. It is also called the resolution.

In the example: Shift the tests to Wednesday and start an early bus on Mondays.

8.1 What is data storytelling?

Data storytelling is the skill of communicating insights from data using three elements - data, narrative and visuals - so that the audience understands, remembers and acts.

Three elements of data storytelling
Data story
Data - accurate analysis
Narrative - the story and context
Visuals - charts and graphics
CombinationResult
Data + narrativeexplains - the audience understands
Data + visualsenlightens - patterns become clear
Narrative + visualsengages - the audience is interested
All threedrives change - the audience acts

8.2 Why stories?

Why data storytelling works
🧠
Memorable

people remember stories more than numbers

❤️
Emotional connection

stories make data meaningful

🎯
Clarity

focuses on the key message

🏃
Action

persuades decision makers

Numbers vs story

Numbers: "Dropout rate rose from 4% to 9%." Story: "Last year, 9 out of every 100 girls in our district left school after Class VIII - more than double the year before. The main reason in our survey: no safe transport. A bus service in 12 villages could bring most of them back."

8.3 Structure of a data story

Narrative arc
1Setting - context and characters
➜
2Rising insight - the problem appears
➜
3Climax - the key finding (aha moment)
➜
4Resolution - recommendation
➜
5Call to action
PartContent
Beginningcontext, why the topic matters, the question
Middledata findings, comparisons, the key insight
Endconclusion, recommendation, what the audience should do

8.4 Steps to create a data story

Steps
1Know the audience
➜
2Define the key message
➜
3Collect and analyse data
➜
4Choose the right visuals
➜
5Build the narrative
➜
6Review, simplify and present
StepQuestions
AudienceWho are they? What do they know? What do they need?
MessageWhat one sentence should they remember?
DataIs it accurate, complete and relevant?
VisualsWhich chart shows the message best?
NarrativeWhat is the beginning, middle and end?
ReviewCan anything be removed without losing meaning?

8.5 Choosing visuals

PurposeBest chart
Compare categoriesbar / column chart
Trend over timeline chart
Part of a wholepie or donut (few parts), stacked bar
Relationshipscatter plot
Distributionhistogram, box plot
Geographymap
Key single numberbig-number card (KPI)
Design tips
🎯
Highlight

use one strong colour for the key point

🧹
Declutter

remove gridlines, 3-D, extra labels

🏷️
Label clearly

titles that state the insight

📏
Honest axes

start bar charts at zero

8.6 Ethics in data storytelling

Honest vs misleading
Honest
  • full context
  • axes start at zero for bars
  • sources cited
  • uncertainty shown
VS
Misleading
  • cherry-picked data
  • truncated or stretched axes
  • missing sources
  • correlation shown as cause
Common mistake

A chart whose y-axis starts at 95 instead of 0 can make a 2% change look huge. Always check the axes.

8.7 Tools

Excel / Google Sheets charts, Tableau, Power BI, Flourish, Datawrapper, Canva infographics and Python (Matplotlib, Seaborn, Plotly).

import matplotlib.pyplot as plt
years = [2021, 2022, 2023, 2024]
users = [20, 35, 60, 95]
plt.plot(years, users, marker="o")
plt.title("UPI users in our town grew almost 5 times in 4 years")
plt.ylabel("Users (thousands)")
plt.show()

8.8 Case study

Case study: Covid-19 dashboards

During the pandemic, dashboards showed daily cases, recoveries and vaccinations with maps and line charts. A clear message ("cases are rising in these districts"), simple visuals and a call to action ("get vaccinated, wear masks") helped people and governments act quickly - data storytelling in real life.

8.9 Exam-ready answers

Q. Name the three elements of data storytelling. (2 marks)

Data, narrative and visuals.

Q. Explain the steps to create an effective data story. (4 marks)

Know your audience; define one key message; collect and analyse accurate data; choose suitable visuals; build a narrative with a beginning, middle and end; review and simplify; then present with a clear call to action.

Quick revision: one-look summary

Data storytelling means presenting the insights of data as a story, so that the audience understands, remembers and acts.

Picture: data, narrative and visuals

DataNarrativeVisualsexplainenlightenengageCHANGE

In daily life: A cricket commentator: the scorecard is the data, the commentary is the narrative, the replay graphics are the visuals.

Picture: Freytag's Pyramid

IntroductionClimaxConclusionRising actionFalling actionmain insightbackgroundwhat to do
Build up to the main insight (climax), then lead the audience to the conclusion.

Which visual for which data

Type of dataVisualisation
TextWord cloud
NumericLine graph, bar chart, pie chart, scatter plot, histogram, heat map
StocksCandlestick chart
GeographicMap chart
MixedFacet grid

Four steps to create a data story

  1. Collect the data and organise it
  2. Use proper visualisation tools to visualise the data
  3. Observe the relationships in the data
  4. Create a simple narrative, hidden in the data, for the audience

Ethics in data storytelling

  • Accuracy: keep the data reliable; do not change it to fit the story
  • Transparency: name the sources, methods and limits
  • Respect for privacy: do not share personal data without consent

More in detail

Tap and learnChart chooser

Tap what you want to show; see the chart that fits.

A change over time

Chart: Line graph

Example: temperature of a week, sales of twelve months

A comparison of separate items

Chart: Bar chart

Example: marks of five students, sales of four products

Parts of a whole

Chart: Pie chart

Example: share of each house in the total points

The relation between two numbers

Chart: Scatter plot

Example: study hours against marks

How often each range of values occurs

Chart: Histogram

Example: number of students in each range of marks

The most frequent words of a text

Chart: Word cloud

Example: feedback comments of parents

Data of different places

Chart: Map chart

Example: rainfall of the states of India

Opening, closing, high and low prices

Chart: Candlestick chart

Example: daily price of a share

Many categories compared by colour

Chart: Heat map

Example: attendance of each class in each month

Five elements of a story

ElementIn any storyIn the attendance data story
Charactersthe people of the storythe students who travel far
Plot / Settingthe order of events; where and when they happenthe school, this session, Monday after Monday
Conflictthe problem that drives the storyattendance falls every Monday
Resolutionhow the problem is solvedtests on Wednesday, an early bus on Monday
Insightswhat the audience learnsdistance from school affects attendance

Data, narrative and visuals together

CombinationResultMeaning
Data + NarrativeExplainthe story tells what is happening in the data and why
Data + VisualsEnlightenthe audience sees the data in a new way
Narrative + VisualsEngagethe audience stays interested
Data + Narrative + VisualsChangethe story moves people to act

Data visualisation and data storytelling

Data visualisationData storytelling
Hascharts and graphscharts, a narrative and the data
Tellswhat the data looks likewhat it means and what to do
Audiencehas to find the insightis led to the insight

Why data storytelling is powerful

  • Memorable: a story is remembered longer than plain numbers
  • Persuasive: it convinces both business and technical people
  • Engaging: it holds the attention of the audience
Remember

The CBSE handbook names the five stages as introduction, rising action, climax, falling action and conclusion. Use these names in the paper.

GamePut Freytag's Pyramid in order

Tap the five stages of a data story from first to last.

GameWhich chart fits?

Read what is to be shown and tap the chart.

Open its questions
10

Question bank: every type, with answers

889 questions in 15 types, including 213 numericals with full working

SQP 2026-27 42 questions follow the CBSE sample paper (shortened and reworded) Practice 847 written on the same pattern

Tap a type to open it. In the one-mark types, tap an option to check yourself. The answers of all the numericals were worked out by a program.

Objective type · 1 mark each

A1Employability skills MCQ1 mark · 95 questions
A1.1Practice1 mark

In the acronym RESPECT for active listening, the letter P stands for

Answer

(b) Pay attention to what the speaker is saying P = Pay attention to what the speaker is saying (look at the speaker, avoid distractions).

A1.2Practice1 mark

Which is the first stage of active listening?

Answer

(b) Receiving Active listening starts with Receiving (hearing the message).

A1.3Practice1 mark

Which is the correct order of the stages of active listening?

Answer

(a) Receiving, Understanding, Remembering, Evaluating, Responding Receive the message, understand it, remember it, evaluate it, then respond.

A1.4Practice1 mark

In the capitalisation rule MINTS, the letter N stands for

Answer

(d) Names MINTS: Months, I, Names, Titles, Starting letter of sentences.

A1.5Practice1 mark

"The ball was hit by Rohit." This sentence is in the

Answer

(b) passive voice The receiver of the action (ball) is the subject and 'by Rohit' tells the doer, so it is passive voice.

A1.6Practice1 mark

Which part of speech describes a noun?

Answer

(c) Adjective An adjective describes a noun, e.g. 'a red ball'.

A1.7Practice1 mark

In the sentence "She quickly finished the work", the word 'quickly' is

Answer

(a) an adverb 'quickly' tells how she finished (describes the verb), so it is an adverb.

A1.8Practice1 mark

Which of these is a barrier to active listening?

Answer

(a) Thinking about your reply while the other person is speaking Planning your reply stops you from listening fully to the speaker.

A1.9Practice1 mark

A group of sentences on one idea is called a

Answer

(a) paragraph A paragraph is a group of sentences about one idea.

A1.10Practice1 mark

"Please close the door." This is

Answer

(d) an imperative sentence It is a request/command, so it is an imperative sentence.

A1.11Practice1 mark

In RESPECT, the letter C stands for

Answer

(c) Clarify your doubts C = Clarify your doubts by asking questions.

A1.12SQP 2026-271 mark

A person who does not trust others and holds grudges for a long time may have

Answer

(c) paranoid personality disorder Constant suspicion and grudges are signs of paranoid personality disorder.

A1.13SQP 2026-271 mark

Doing an activity for the joy of it, without any reward from outside, is

Answer

(b) intrinsic motivation Motivation from inside (joy, interest) is intrinsic motivation.

A1.14SQP 2026-271 mark

Continuing to work towards a goal in spite of difficulties is called

Answer

(c) perseverance Perseverance means not giving up when things are hard.

A1.15Practice1 mark

Which of these is NOT one of the Big Five personality factors?

Answer

(d) Punctuality The Big Five (OCEAN) are Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism; punctuality is not one.

A1.16Practice1 mark

A person who is talkative, outgoing and full of energy is high in

Answer

(b) extraversion Extraversion means being outgoing, social and energetic.

A1.17Practice1 mark

A person who is organised, careful and dependable is high in

Answer

(c) conscientiousness Conscientiousness means being organised and dependable.

A1.18Practice1 mark

A person who is curious, creative and likes new ideas is high in

Answer

(c) openness Openness (to experience) means curiosity and creativity.

A1.19Practice1 mark

A person who gets upset easily and often feels anxious is high in

Answer

(d) neuroticism (low emotional stability) Neuroticism (low emotional stability) means getting upset and anxious easily.

A1.20Practice1 mark

Working for a salary hike or a prize is an example of

Answer

(d) extrinsic motivation An outside reward is extrinsic motivation.

A1.21Practice1 mark

Paranoid, schizoid and schizotypal personality disorders belong to

Answer

(c) Cluster A (suspicious) Cluster A disorders involve odd or suspicious behaviour.

A1.22Practice1 mark

Antisocial, borderline, histrionic and narcissistic personality disorders belong to

Answer

(c) Cluster B (emotional and impulsive) Cluster B disorders involve dramatic, emotional or impulsive behaviour.

A1.23Practice1 mark

Avoidant, dependent and obsessive-compulsive personality disorders belong to

Answer

(c) Cluster C (anxious) Cluster C disorders involve anxious or fearful behaviour.

A1.24Practice1 mark

A person who believes he is more important than everyone else and wants constant praise may have

Answer

(c) narcissistic personality disorder An inflated sense of importance and need for praise point to narcissistic personality disorder.

A1.25Practice1 mark

A person who avoids social gatherings for fear of being criticised may have

Answer

(d) avoidant personality disorder Avoiding people for fear of criticism is a sign of avoidant personality disorder.

A1.26Practice1 mark

Focusing on the goal and finishing the work in the given time is called

Answer

(b) result orientation Result orientation means focusing on the result and the deadline.

A1.27Practice1 mark

Which of these helps a person to become result oriented?

Answer

(c) Setting clear goals and preparing an action plan Clear goals and an action plan keep the work focused on results.

A1.28Practice1 mark

Knowing your own strengths and weaknesses is called

Answer

(d) self-awareness Self-awareness means knowing yourself.

A1.29Practice1 mark

A person who depends on others for every decision may have

Answer

(c) dependent personality disorder Needing others for every decision is a sign of dependent personality disorder.

A1.30Practice1 mark

A person who is kind, cooperative and trusts others is high in

Answer

(b) agreeableness Agreeableness means being kind, cooperative and trusting.

A1.31Practice1 mark

A positive attitude helps a person to

Answer

(b) face challenges and reduce stress A positive outlook helps to face challenges and lowers stress.

A1.32Practice1 mark

Which step can help a person with a personality disorder?

Answer

(c) Talking to a counsellor or a trusted person Talking to a counsellor or trusted person is the first step to getting help.

A1.33SQP 2026-271 mark

Which is the odd one out among these spreadsheet programs?

Answer

(b) Tableau Tableau is a data visualisation tool, not a spreadsheet.

A1.34Practice1 mark

In a spreadsheet, the box where a row and a column meet is called a

Answer

(d) cell The meeting point of a row and a column is a cell.

A1.35Practice1 mark

Every formula in a spreadsheet begins with the sign

Answer

(a) = Formulas start with =, e.g. =A1+B1.

A1.36Practice1 mark

Which function adds the numbers in the cells A1 to A5?

Answer

(b) =SUM(A1:A5) =SUM(A1:A5) adds the range A1 to A5.

A1.37Practice1 mark

Which feature shows only the rows that meet a condition and hides the rest?

Answer

(a) Filter A filter shows only the matching rows.

A1.38Practice1 mark

Arranging the data of a column from A to Z is called

Answer

(a) sorting Sorting arranges data in order (A to Z or Z to A).

A1.39Practice1 mark

The address of the cell in column C and row 4 is

Answer

(d) C4 A cell address is column letter + row number: C4.

A1.40Practice1 mark

Which of these is presentation software?

Answer

(c) LibreOffice Impress LibreOffice Impress (like PowerPoint) makes presentations.

A1.41Practice1 mark

One page of a presentation is called a

Answer

(d) slide Each page of a presentation is a slide.

A1.42Practice1 mark

Which function gives the average of the cells B2 to B6?

Answer

(b) =AVERAGE(B2:B6) =AVERAGE(B2:B6) gives the mean of the range.

A1.43Practice1 mark

Giving a password to a spreadsheet so that others cannot change it is called

Answer

(d) protecting the spreadsheet Protecting the sheet with a password stops unwanted changes.

A1.44Practice1 mark

A person who starts a business with a new idea, taking a risk to earn profit, is an

Answer

(a) entrepreneur An entrepreneur takes a risk to start a business.

A1.45Practice1 mark

Entrepreneurs who buy and sell goods but do not manufacture them are

Answer

(c) business (trading) entrepreneurs Trading entrepreneurs buy and sell goods.

A1.46Practice1 mark

Entrepreneurs who manufacture products are called

Answer

(b) industrial entrepreneurs Industrial (manufacturing) entrepreneurs make products.

A1.47Practice1 mark

A person who runs a coaching centre or a salon is a

Answer

(b) service entrepreneur They sell services, not goods: service entrepreneurs.

A1.48Practice1 mark

The ability to take a decision quickly and firmly is called

Answer

(d) decisiveness Decisiveness is taking quick, firm decisions.

A1.49Practice1 mark

Starting a task on your own, without being told, shows

Answer

(d) initiative Taking the first step without being told is initiative.

A1.50Practice1 mark

Which of these is a barrier to entrepreneurship?

Answer

(a) A faulty or missing business plan A weak or missing business plan makes the business fail.

A1.51Practice1 mark

Self-doubt and fear of failure are

Answer

(a) personal barriers to entrepreneurship They come from within the person, so they are personal barriers.

A1.52Practice1 mark

Lack of raw material, labour or good roads is

Answer

(d) an environmental barrier These come from the surroundings, so they are environmental barriers.

A1.53Practice1 mark

The ability to plan, arrange resources and manage time well is called

Answer

(b) organisational skills Organisational skills are about planning and managing.

A1.54Practice1 mark

The ability to work well with others, listen and build relations is called

Answer

(d) interpersonal skills Interpersonal skills help us work with people.

A1.55SQP 2026-271 mark

Which of these is NOT a greenhouse gas?

Answer

(b) Oxygen Oxygen does not trap heat; CO₂, methane and nitrous oxide do.

A1.56Practice1 mark

Jobs that help to protect or restore the environment are called

Answer

(b) green jobs Green jobs protect or restore the environment.

A1.57Practice1 mark

NAPCC stands for

Answer

(b) National Action Plan on Climate Change NAPCC = National Action Plan on Climate Change.

A1.58Practice1 mark

The National Action Plan on Climate Change was launched in the year

Answer

(d) 2008 India launched the NAPCC in 2008.

A1.59Practice1 mark

A technician who installs solar panels has a green job in the field of

Answer

(a) renewable energy Solar power is renewable energy.

A1.60Practice1 mark

A guide who takes tourists to a forest without harming nature works in

Answer

(d) eco-tourism Tourism that protects nature is eco-tourism.

A1.61Practice1 mark

Small-scale, low-cost technology that suits local needs and does not harm the environment is called

Answer

(c) appropriate technology Appropriate technology fits local needs and the environment.

A1.62Practice1 mark

Which of these is a green job in agriculture?

Answer

(b) Organic farming Organic farming avoids chemical fertilisers and pesticides.

A1.63Practice1 mark

Which of these is a benefit of green jobs?

Answer

(c) They reduce waste and pollution Green jobs cut waste and pollution.

A1.64Practice1 mark

Which of these is a non-renewable source of energy?

Answer

(a) Natural gas Natural gas is a fossil fuel; once used it cannot be replaced.

A1.65Practice1 mark

Collecting rainwater from roofs and storing it is a green practice in

Answer

(c) water conservation Rainwater harvesting conserves water.

A1.66Practice1 mark

Which stage of active listening involves judging the message and deciding whether it is useful?

Answer

(d) Evaluating Evaluating means judging the message.

A1.67Practice1 mark

In RESPECT, the first letter R stands for

Answer

(a) Remove distractions R = Remove distractions.

A1.68Practice1 mark

Which word is a conjunction in the sentence "Ravi and Meena went home"?

Answer

(b) and 'and' joins two words, so it is a conjunction.

A1.69Practice1 mark

"What a beautiful painting!" is

Answer

(d) an exclamatory sentence It shows strong feeling and ends with !, so it is exclamatory.

A1.70Practice1 mark

Which of these shows active listening?

Answer

(b) Asking a question to clarify a doubt Asking to clarify shows you are listening and want to understand.

A1.71Practice1 mark

A person who seeks attention all the time and is overly dramatic may have

Answer

(b) histrionic personality disorder Attention-seeking and dramatic behaviour point to histrionic personality disorder.

A1.72Practice1 mark

A person who wants everything in perfect order and control may have

Answer

(a) obsessive-compulsive personality disorder Excessive need for order and control is obsessive-compulsive personality disorder.

A1.73Practice1 mark

A person who prefers to stay alone and shows little emotion may have

Answer

(c) schizoid personality disorder Liking to be alone with little emotion is schizoid personality disorder.

A1.74Practice1 mark

A person who breaks rules and does not care about the feelings of others may have

Answer

(b) antisocial personality disorder Ignoring rules and others' feelings points to antisocial personality disorder.

A1.75Practice1 mark

The Big Five personality factors are remembered by the word

Answer

(b) OCEAN Openness, Conscientiousness, Extraversion, Agreeableness, Neuroticism.

A1.76Practice1 mark

Which of these is a source of intrinsic motivation?

Answer

(c) Interest in the subject Interest in the subject comes from inside.

A1.77Practice1 mark

Which of these shows a positive attitude?

Answer

(c) Treating a failure as a chance to learn Seeing failure as a chance to learn is a positive attitude.

A1.78Practice1 mark

A result-oriented person

Answer

(a) plans the work and finishes it in the given time A result-oriented person plans and finishes the work on time.

A1.79Practice1 mark

Unstable moods and unstable relations are signs of

Answer

(b) borderline personality disorder Unstable moods and relationships are signs of borderline personality disorder.

A1.80Practice1 mark

A calm person who is not easily upset is low in

Answer

(d) neuroticism Low neuroticism = emotionally stable and calm.

A1.81Practice1 mark

Which function gives the smallest value in the cells A1 to A10?

Answer

(c) =MIN(A1:A10) =MIN(A1:A10) gives the smallest value.

A1.82Practice1 mark

Which function counts the cells that contain numbers?

Answer

(d) COUNT COUNT counts cells with numbers; COUNTA counts non-empty cells.

A1.83Practice1 mark

Which key starts the slide show from the first slide in LibreOffice Impress?

Answer

(b) F5 F5 starts the slide show from the first slide.

A1.84Practice1 mark

A pictorial form of the data of a spreadsheet is called a

Answer

(d) chart A chart shows the data as a picture.

A1.85Practice1 mark

In the formula =B2*C2, the sign * means

Answer

(d) multiplication * is multiplication in spreadsheets.

A1.86Practice1 mark

Entrepreneurs who work in farming, dairy or poultry are

Answer

(a) agricultural entrepreneurs They work in agriculture: agricultural entrepreneurs.

A1.87Practice1 mark

An entrepreneur whose main aim is to solve a problem of society is a

Answer

(c) social entrepreneur A social entrepreneur's main aim is social good.

A1.88Practice1 mark

Which competency helps an entrepreneur to lead a team and deal with customers?

Answer

(c) Interpersonal skills Interpersonal skills help in dealing with people.

A1.89Practice1 mark

Seeing a problem as an opportunity is an entrepreneurial

Answer

(c) attitude This way of thinking is an entrepreneurial attitude.

A1.90Practice1 mark

A person who takes the first step to start a new activity shows

Answer

(b) initiative Taking the first step is initiative.

A1.91Practice1 mark

Which of these is a greenhouse gas?

Answer

(b) Methane Methane traps heat in the atmosphere.

A1.92Practice1 mark

How many national missions are there in the NAPCC?

Answer

(d) 8 The NAPCC has 8 national missions (e.g. solar, energy efficiency, water).

A1.93Practice1 mark

A worker who separates dry and wet waste for recycling has a green job in

Answer

(b) solid waste management Sorting waste for recycling is solid waste management.

A1.94Practice1 mark

A driver of an electric bus has a green job in the field of

Answer

(d) transportation Clean transport reduces pollution.

A1.95Practice1 mark

Which of these is a renewable source of energy?

Answer

(c) Solar energy Solar energy is renewed naturally.

A2Data science methodology MCQ, with numericals1 mark · 87 questions
A2.1SQP 2026-271 mark

RMSE stands for

Answer

(d) Root Mean Square Error RMSE = Root Mean Square Error.

A2.2SQP 2026-271 mark

A team is deciding whether its problem needs classification or regression. In which step of the Data Science Methodology is this done?

Answer

(d) Analytic Approach Choosing the type of model is done in the Analytic Approach step.

A2.3SQP 2026-271 mark

Which activity is NOT a part of the Data Requirements step?

Answer

(a) Extracting the data from the sources Extracting the data belongs to Data Collection.

A2.4Practice1 mark

In 10-fold cross validation of 1000 records, how many records are used for training in each round?

Answer

(a) 900 One fold (100 records) is kept for testing; the other 9 folds train the model.

A2.5Practice1 mark

A model gave these results on the test data: TP = 9, FP = 6, FN = 11 and TN = 24. What is its recall?

Answer

(c) 0.45 Recall = TP / (TP + FN) = 9 / 20.

A2.6Practice1 mark

A hospital wants to know why more patients came back within a month. Which analytic approach is this?

Answer

(c) Diagnostic 'Why did it happen?' is a diagnostic question.

A2.7Practice1 mark

Which is the first step of the Data Science Methodology?

Answer

(d) Business Understanding It starts with Business Understanding: what is the problem?

A2.8Practice1 mark

In k-fold cross validation, the data is divided into

Answer

(a) k equal parts (folds) The data is split into k equal folds; each fold is used once for testing.

A2.9Practice1 mark

A model gave these results on the test data: TP = 24, FP = 24, FN = 8 and TN = 44. What is its precision?

Answer

(c) 0.50 Precision = TP / (TP + FP) = 24 / 48.

A2.10Practice1 mark

A model gave these results on the test data: TP = 9, FP = 3, FN = 9 and TN = 29. What is its recall?

Answer

(c) 0.50 Recall = TP / (TP + FN) = 9 / 18.

A2.11Practice1 mark

A model predicted the price of a bicycle (in rupees) as 224. The actual value was 200. What is the accuracy of this prediction?

Answer

(d) 88% Error = 24. Error rate = 24 / 200 = 12%. Accuracy = 100% - 12% = 88%.

A2.12Practice1 mark

A model gave these results on the test data: TP = 18, FP = 2, FN = 18 and TN = 62. What is its precision?

Answer

(a) 0.90 Precision = TP / (TP + FP) = 18 / 20.

A2.13Practice1 mark

A model predicted the price of a bicycle (in rupees) as 550. The actual value was 500. What is the accuracy of this prediction?

Answer

(a) 90% Error = 50. Error rate = 50 / 500 = 10%. Accuracy = 100% - 10% = 90%.

A2.14Practice1 mark

"Where is the data coming from and how will you get it?" This question is asked in

Answer

(a) Data Collection This is asked in Data Collection.

A2.15Practice1 mark

The errors (actual - predicted) of a regression model on 4 cases are 3, 3, 3, 3. What is the Mean Squared Error?

Answer

(d) 9 Squares: 9, 9, 9, 9. MSE = 36 / 4 = 9.

A2.16Practice1 mark

A model gave these results on the test data: TP = 24, FP = 26, FN = 8 and TN = 42. What is its recall?

Answer

(d) 0.75 Recall = TP / (TP + FN) = 24 / 32.

A2.17Practice1 mark

A model gave these results on the test data: TP = 26, FP = 14, FN = 24 and TN = 36. What is its precision?

Answer

(c) 0.65 Precision = TP / (TP + FP) = 26 / 40.

A2.18Practice1 mark

"What is the problem that you are trying to solve?" This question is asked in

Answer

(a) Business Understanding This is the question of Business Understanding.

A2.19Practice1 mark

A model gave these results on the test data: TP = 26, FP = 26, FN = 14 and TN = 34. What is its accuracy?

Answer

(b) 60% Accuracy = (TP + TN) / Total = 60 / 100.

A2.20Practice1 mark

The Mean Squared Error of a model is 25. What is its RMSE?

Answer

(d) 5 RMSE is the square root of MSE.

A2.21Practice1 mark

Removing wrong and missing values and making new useful columns is done in

Answer

(b) Data Preparation Cleaning and feature making are done in Data Preparation.

A2.22Practice1 mark

Which is a disadvantage of cross validation compared with a simple train-test split?

Answer

(a) It needs more computing time The model is trained k times, so it needs more computing time.

A2.23Practice1 mark

A lower value of RMSE means that the regression model is

Answer

(d) better Lower error means predictions are closer to actual values.

A2.24Practice1 mark

Which is the most time-consuming step of the methodology?

Answer

(c) Data Preparation Data Preparation (cleaning, transforming) usually takes most of the time.

A2.25Practice1 mark

A model gave these results on the test data: TP = 112, FP = 28, FN = 48 and TN = 12. What is its recall?

Answer

(d) 0.70 Recall = TP / (TP + FN) = 112 / 160.

A2.26Practice1 mark

A model gave these results on the test data: TP = 21, FP = 14, FN = 4 and TN = 11. What is its precision?

Answer

(a) 0.60 Precision = TP / (TP + FP) = 21 / 35.

A2.27Practice1 mark

A model gave these results on the test data: TP = 26, FP = 14, FN = 26 and TN = 34. What is its precision?

Answer

(a) 0.65 Precision = TP / (TP + FP) = 26 / 40.

A2.28Practice1 mark

The Mean Squared Error of a model is 25. What is its RMSE?

Answer

(c) 5 RMSE is the square root of MSE.

A2.29Practice1 mark

A model gave these results on the test data: TP = 36, FP = 4, FN = 44 and TN = 116. What is its accuracy?

Answer

(b) 76% Accuracy = (TP + TN) / Total = 152 / 200.

A2.30Practice1 mark

A model gave these results on the test data: TP = 12, FP = 4, FN = 3 and TN = 31. What is its recall?

Answer

(d) 0.80 Recall = TP / (TP + FN) = 12 / 15.

A2.31Practice1 mark

A model predicted the number of visitors to a fair as 540. The actual value was 500. What is the accuracy of this prediction?

Answer

(c) 92% Error = 40. Error rate = 40 / 500 = 8%. Accuracy = 100% - 8% = 92%.

A2.32Practice1 mark

A data set of 400 records is split 70:30 into training and testing data. How many records are used for testing?

Answer

(b) 120 Testing part = 30% of 400.

A2.33Practice1 mark

The Evaluation step has two phases. They are

Answer

(a) diagnostic measures phase and statistical significance phase Evaluation has a diagnostic measures phase and a statistical significance phase.

A2.34Practice1 mark

A model gave these results on the test data: TP = 15, FP = 5, FN = 10 and TN = 20. What is its accuracy?

Answer

(a) 70% Accuracy = (TP + TN) / Total = 35 / 50.

A2.35Practice1 mark

A data set of 500 records is used for 5-fold cross validation. How many records are there in each fold (test set)?

Answer

(a) 100 Each fold has 500 / 5 records.

A2.36Practice1 mark

Using domain knowledge to create new features from raw data is called

Answer

(d) feature engineering Feature engineering builds useful new features.

A2.37Practice1 mark

A model predicted the number of visitors to a fair as 360. The actual value was 400. What is the accuracy of this prediction?

Answer

(b) 90% Error = 40. Error rate = 40 / 400 = 10%. Accuracy = 100% - 10% = 90%.

A2.38Practice1 mark

A data set of 500 records is split 70:30 into training and testing data. How many records are used for testing?

Answer

(b) 150 Testing part = 30% of 500.

A2.39Practice1 mark

The value of MSE can never be

Answer

(d) negative Errors are squared, so every term is zero or positive.

A2.40Practice1 mark

Making the model available to the users is the step of

Answer

(d) Deployment Deployment puts the model into use.

A2.41Practice1 mark

A model gave these results on the test data: TP = 36, FP = 24, FN = 12 and TN = 28. What is its accuracy?

Answer

(b) 64% Accuracy = (TP + TN) / Total = 64 / 100.

A2.42Practice1 mark

A model that forecasts a future outcome, such as whether a customer will leave, is a

Answer

(b) predictive model Forecasting the future is predictive.

A2.43Practice1 mark

Which metric is used for a classification model?

Answer

(a) F1 score F1 score (with accuracy, precision, recall) is used for classification.

A2.44Practice1 mark

A model gave these results on the test data: TP = 84, FP = 16, FN = 28 and TN = 72. What is its accuracy?

Answer

(a) 78% Accuracy = (TP + TN) / Total = 156 / 200.

A2.45Practice1 mark

A model made 320 correct predictions out of 400 test cases. What is its accuracy?

Answer

(a) 80% Accuracy = correct predictions / total predictions = 320 / 400.

A2.46Practice1 mark

A model made 800 correct predictions out of 1000 test cases. What is its accuracy?

Answer

(a) 80% Accuracy = correct predictions / total predictions = 800 / 1000.

A2.47Practice1 mark

A model gave these results on the test data: TP = 18, FP = 6, FN = 22 and TN = 54. What is its precision?

Answer

(c) 0.75 Precision = TP / (TP + FP) = 18 / 24.

A2.48Practice1 mark

An analytic approach that answers "Why did it happen?" is

Answer

(c) diagnostic Diagnostic analytics finds the reasons.

A2.49Practice1 mark

An analytic approach that answers "What will happen?" is

Answer

(c) predictive Predictive analytics forecasts the future.

A2.50Practice1 mark

"What data do you need to answer the question?" This question is asked in

Answer

(c) Data Requirements This is asked in Data Requirements.

A2.51Practice1 mark

A model made 320 correct predictions out of 400 test cases. What is its accuracy?

Answer

(d) 80% Accuracy = correct predictions / total predictions = 320 / 400.

A2.52Practice1 mark

Which metric is used for a regression model?

Answer

(c) RMSE RMSE (and MSE, MAE) measures the error of number predictions.

A2.53Practice1 mark

MAE stands for

Answer

(b) Mean Absolute Error MAE = Mean Absolute Error.

A2.54Practice1 mark

A data set of 200 records is split 70:30 into training and testing data. How many records are used for testing?

Answer

(b) 60 Testing part = 30% of 200.

A2.55Practice1 mark

An analytic approach that answers "What happened?" is

Answer

(d) descriptive Descriptive analytics summarises past data.

A2.56Practice1 mark

The Mean Squared Error of a model is 9. What is its RMSE?

Answer

(d) 3 RMSE is the square root of MSE.

A2.57Practice1 mark

A model predicted the runs scored by a team as 736. The actual value was 800. What is the error rate?

Answer

(b) 8% Error = 64. Error rate = error / actual value = 64 / 800 = 8%.

A2.58Practice1 mark

A model gave these results on the test data: TP = 60, FP = 40, FN = 20 and TN = 80. What is its accuracy?

Answer

(d) 70% Accuracy = (TP + TN) / Total = 140 / 200.

A2.59Practice1 mark

A model gave these results on the test data: TP = 52, FP = 52, FN = 48 and TN = 48. What is its precision?

Answer

(b) 0.50 Precision = TP / (TP + FP) = 52 / 104.

A2.60Practice1 mark

A model predicted the weight of a parcel (in grams) as 960. The actual value was 800. What is the error rate?

Answer

(a) 20% Error = 160. Error rate = error / actual value = 160 / 800 = 20%.

A2.61Practice1 mark

A model gave these results on the test data: TP = 28, FP = 22, FN = 28 and TN = 22. What is its accuracy?

Answer

(c) 50% Accuracy = (TP + TN) / Total = 50 / 100.

A2.62Practice1 mark

A model gave these results on the test data: TP = 24, FP = 26, FN = 8 and TN = 42. What is its recall?

Answer

(b) 0.75 Recall = TP / (TP + FN) = 24 / 32.

A2.63Practice1 mark

"Is the data that you collected representative of the problem to be solved?" This question is asked in

Answer

(c) Data Understanding This is checked in Data Understanding.

A2.64Practice1 mark

A model predicted the runs scored by a team as 525. The actual value was 500. What is the error rate?

Answer

(c) 5% Error = 25. Error rate = error / actual value = 25 / 500 = 5%.

A2.65Practice1 mark

A shop wants to forecast its sales for next Diwali. Which analytic approach is this?

Answer

(a) Predictive Forecasting future sales is predictive.

A2.66Practice1 mark

A model that summarises past data to show patterns, such as clusters of customers, is a

Answer

(d) descriptive model Summarising and finding patterns in past data is descriptive.

A2.67Practice1 mark

How many steps are there in the Data Science Methodology?

Answer

(c) 10 John Rollins' methodology has 10 steps.

A2.68Practice1 mark

A model gave these results on the test data: TP = 48, FP = 16, FN = 12 and TN = 124. What is its precision?

Answer

(b) 0.75 Precision = TP / (TP + FP) = 48 / 64.

A2.69Practice1 mark

A model gave these results on the test data: TP = 54, FP = 6, FN = 18 and TN = 22. What is its recall?

Answer

(c) 0.75 Recall = TP / (TP + FN) = 54 / 72.

A2.70Practice1 mark

The errors (actual - predicted) of a regression model on 4 cases are -5, -3, -1, -1. What is the Mean Squared Error?

Answer

(a) 9 Squares: 25, 9, 1, 1. MSE = 36 / 4 = 9.

A2.71Practice1 mark

A model gave these results on the test data: TP = 18, FP = 7, FN = 12 and TN = 13. What is its recall?

Answer

(d) 0.60 Recall = TP / (TP + FN) = 18 / 30.

A2.72Practice1 mark

The errors (actual - predicted) of a regression model on 4 cases are -7, -5, -1, -5. What is the Mean Squared Error?

Answer

(a) 25 Squares: 49, 25, 1, 25. MSE = 100 / 4 = 25.

A2.73Practice1 mark

The Mean Squared Error of a model is 25. What is its RMSE?

Answer

(c) 5 RMSE is the square root of MSE.

A2.74Practice1 mark

A model gave these results on the test data: TP = 18, FP = 18, FN = 12 and TN = 52. What is its accuracy?

Answer

(b) 70% Accuracy = (TP + TN) / Total = 70 / 100.

A2.75Practice1 mark

Which is the last step of the Data Science Methodology?

Answer

(c) Feedback Feedback is the last step; it is used to improve the model.

A2.76Practice1 mark

A data set of 1200 records is used for 6-fold cross validation. How many records are there in each fold (test set)?

Answer

(d) 200 Each fold has 1200 / 6 records.

A2.77Practice1 mark

A data set of 200 records is used for 4-fold cross validation. How many records are there in each fold (test set)?

Answer

(c) 50 Each fold has 200 / 4 records.

A2.78Practice1 mark

In 3-fold cross validation of 600 records, how many records are used for training in each round?

Answer

(a) 400 One fold (200 records) is kept for testing; the other 2 folds train the model.

A2.79Practice1 mark

A model predicted the weight of a parcel (in grams) as 360. The actual value was 400. What is the error rate?

Answer

(d) 10% Error = 40. Error rate = error / actual value = 40 / 400 = 10%.

A2.80Practice1 mark

The Data Science Methodology was given by

Answer

(b) John Rollins of IBM It was given by John Rollins of IBM.

A2.81Practice1 mark

A model gave these results on the test data: TP = 44, FP = 44, FN = 36 and TN = 76. What is its precision?

Answer

(b) 0.50 Precision = TP / (TP + FP) = 44 / 88.

A2.82Practice1 mark

In 4-fold cross validation of 800 records, how many records are used for training in each round?

Answer

(a) 600 One fold (200 records) is kept for testing; the other 3 folds train the model.

A2.83Practice1 mark

A model gave these results on the test data: TP = 21, FP = 14, FN = 7 and TN = 8. What is its recall?

Answer

(a) 0.75 Recall = TP / (TP + FN) = 21 / 28.

A2.84Practice1 mark

A model gave these results on the test data: TP = 16, FP = 16, FN = 24 and TN = 44. What is its accuracy?

Answer

(a) 60% Accuracy = (TP + TN) / Total = 60 / 100.

A2.85Practice1 mark

"How can you use the data to answer the question?" This question is asked in

Answer

(d) Analytic Approach This is decided in the Analytic Approach.

A2.86Practice1 mark

An analytic approach that answers "What should be done?" is

Answer

(b) prescriptive Prescriptive analytics recommends actions.

A2.87Practice1 mark

The errors (actual - predicted) of a regression model on 4 cases are 4, -4, -4, 4. What is the Mean Squared Error?

Answer

(c) 16 Squares: 16, 16, 16, 16. MSE = 64 / 4 = 16.

A3Making machines see MCQ, with pixel numericals1 mark · 64 questions
A3.1SQP 2026-271 mark

In the computer vision process, which stage separates the object (for example a fruit) from the background?

Answer

(b) Detection / Segmentation Detection/segmentation separates the object from the background.

A3.2SQP 2026-271 mark

Which is the final stage of the computer vision process, where the image is interpreted and a decision is taken?

Answer

(d) High-level processing High-level processing interprets the image and takes a decision.

A3.3SQP 2026-271 mark

For an image with a single object, the two tasks are

Answer

(a) classification and localisation For one object: classification (what) and localisation (where).

A3.4SQP 2026-271 mark

Which statement about image resolution is INCORRECT?

Answer

(a) A lower resolution image shows more detail A lower resolution has fewer pixels, so it shows LESS detail.

A3.5Practice1 mark

A fake video in which a person's face is replaced using AI is a problem of

Answer

(d) duplicate and false content (deepfake) Such a deepfake is duplicate and false content.

A3.6Practice1 mark

A black-and-white (binary) image has pixel values of

Answer

(c) only 0 and 1 A binary image has only two values: 0 and 1.

A3.7Practice1 mark

A colour (RGB) image has the resolution 50 x 40. How many bytes are needed to store its pixel values without compression?

Answer

(a) 6,000 50 x 40 pixels x 3 bytes.

A3.8Practice1 mark

Which task tells both 'what' the single object is and 'where' it is?

Answer

(d) Classification + localisation Classification gives 'what' and localisation gives 'where'.

A3.9Practice1 mark

An RGB image has the resolution 640 x 480. How many values (numbers) are stored for the whole image?

Answer

(c) 921,600 Each of the 307,200 pixels stores 3 values: red, green and blue.

A3.10Practice1 mark

Capturing an image with a camera, scanner or sensor is called

Answer

(c) image acquisition Getting the image is image acquisition.

A3.11Practice1 mark

Finding the boundaries of objects in an image, where the brightness changes sharply, is

Answer

(c) edge detection Edges are where brightness changes sharply: edge detection.

A3.12Practice1 mark

In an RGB image the pixel (0, 0, 255) is

Answer

(d) blue Only blue at full brightness: blue.

A3.13Practice1 mark

Drawing a box around the single object found in an image is called

Answer

(d) localisation Marking where the object is: localisation.

A3.14Practice1 mark

An 8-bit grayscale image has the resolution 28 x 28. How many bytes are needed to store its pixel values?

Answer

(c) 784 One byte for each pixel: 28 x 28.

A3.15Practice1 mark

The range of pixel values in an 8-bit image is

Answer

(d) 0 to 255 8 bits store 2⁸ = 256 values: 0 to 255.

A3.16Practice1 mark

How many pixels are there in an image of resolution 10 x 5?

Answer

(d) 50 Pixels = width x height.

A3.17Practice1 mark

Computer vision is also known as

Answer

(d) machine vision Computer vision is also called machine vision.

A3.18Practice1 mark

An 8-bit grayscale image has the resolution 4 x 3. How many bytes are needed to store its pixel values?

Answer

(d) 12 One byte for each pixel: 4 x 3.

A3.19Practice1 mark

Which of these is NOT an application of computer vision?

Answer

(c) Chatbot answering typed questions A chatbot works with text, so it is NLP.

A3.20Practice1 mark

An X-ray machine producing a digital image is an example of

Answer

(c) image acquisition Capturing the image is image acquisition.

A3.21Practice1 mark

Which is the first stage of the computer vision process?

Answer

(b) Image acquisition First the image is acquired.

A3.22Practice1 mark

Cutting out the unwanted outer part of an image is called

Answer

(b) cropping Cropping removes the outer part.

A3.23Practice1 mark

Checking fruits on a conveyor belt for defects is an application of computer vision in

Answer

(a) quality inspection in industry Finding defects in products is quality inspection.

A3.24Practice1 mark

How many pixels are there in an image of resolution 28 x 28?

Answer

(a) 784 Pixels = width x height.

A3.25Practice1 mark

Analysing the pattern of a surface, such as smooth or rough, is

Answer

(b) texture analysis Texture analysis studies surface patterns.

A3.26Practice1 mark

What is the total number of pixels in an image that is 300 pixels wide and 200 pixels high?

Answer

(d) 60,000 Width x height.

A3.27Practice1 mark

A camera at a mall counting the number of visitors uses

Answer

(c) object detection Counting people needs finding each one: object detection.

A3.28Practice1 mark

In an RGB image, the pixel (255, 255, 0) is

Answer

(c) yellow Red + green at full brightness make yellow.

A3.29Practice1 mark

A self-driving car uses computer vision mainly to

Answer

(c) detect vehicles, people and traffic signs It must see vehicles, people and signs.

A3.30Practice1 mark

What is the total number of pixels in an image that is 200 pixels wide and 100 pixels high?

Answer

(d) 20,000 Width x height.

A3.31Practice1 mark

An RGB image has the resolution 4 x 3. How many values (numbers) are stored for the whole image?

Answer

(a) 36 Each of the 12 pixels stores 3 values: red, green and blue.

A3.32Practice1 mark

How many channels does an RGB image have?

Answer

(d) 3 Three channels: R, G and B.

A3.33Practice1 mark

Which of these is a challenge of computer vision?

Answer

(d) Privacy and security of people in the images Cameras can capture people without consent: privacy and security.

A3.34Practice1 mark

Labelling every pixel of an image with the class it belongs to, without separating two objects of the same class, is

Answer

(d) semantic segmentation Semantic segmentation labels pixels by class only.

A3.35Practice1 mark

Face unlock in a mobile phone is an application of

Answer

(d) computer vision Recognising a face in a camera image is computer vision.

A3.36Practice1 mark

Which stage of the computer vision process comes just after preprocessing?

Answer

(d) Feature extraction After cleaning (preprocessing), features are extracted.

A3.37Practice1 mark

How many pixels are there in an image of resolution 10 x 5?

Answer

(c) 50 Pixels = width x height.

A3.38Practice1 mark

A colour (RGB) image has the resolution 1024 x 768. How many bytes are needed to store its pixel values without compression?

Answer

(b) 2,359,296 1024 x 768 pixels x 3 bytes.

A3.39Practice1 mark

Counting the cars on a road from a traffic camera needs

Answer

(a) object detection Each car must be found: object detection.

A3.40Practice1 mark

In an 8-bit grayscale image, the pixel value 0 stands for

Answer

(d) black 0 is black.

A3.41Practice1 mark

What is the total number of pixels in an image that is 500 pixels wide and 400 pixels high?

Answer

(b) 200,000 Width x height.

A3.42Practice1 mark

An 8-bit grayscale image has the resolution 64 x 64. How many bytes are needed to store its pixel values?

Answer

(b) 4,096 One byte for each pixel: 64 x 64.

A3.43Practice1 mark

Which is the correct order of the computer vision process?

Answer

(b) Image acquisition, Preprocessing, Feature extraction, Detection/Segmentation, High-level processing Acquire → preprocess → extract features → detect/segment → high-level processing.

A3.44Practice1 mark

Which of these is expected from computer vision in the future?

Answer

(c) Personalised health-care diagnosis and immersive augmented reality Future uses include personalised diagnosis and immersive AR.

A3.45Practice1 mark

Finding many objects in an image and drawing a box around each is

Answer

(b) object detection Many objects with boxes: object detection.

A3.46Practice1 mark

How many pixels are there in an image of resolution 8 x 8?

Answer

(d) 64 Pixels = width x height.

A3.47Practice1 mark

In a grayscale image, the pixel value 255 stands for

Answer

(a) white 255 is white.

A3.48Practice1 mark

Which of these is an application of computer vision in health care?

Answer

(d) Detecting tumours in X-ray and MRI images Finding tumours in scans uses computer vision.

A3.49Practice1 mark

Which library is commonly used in Python for computer vision?

Answer

(b) OpenCV OpenCV (cv2) is the common computer vision library.

A3.50Practice1 mark

What is the total number of pixels in an image that is 800 pixels wide and 600 pixels high?

Answer

(d) 480,000 Width x height.

A3.51Practice1 mark

Which technique improves the contrast of a dull image?

Answer

(a) Histogram equalisation Histogram equalisation spreads out the brightness values to improve contrast.

A3.52Practice1 mark

Edge detection and corner detection are techniques of

Answer

(a) feature extraction They find important features, so they are feature extraction.

A3.53Practice1 mark

Changing the pixel values of all images to a common range, such as 0 to 1, is called

Answer

(a) normalisation Normalisation rescales values to a common range.

A3.54Practice1 mark

A colour (RGB) image has the resolution 1280 x 720. How many bytes are needed to store its pixel values without compression?

Answer

(b) 2,764,800 1280 x 720 pixels x 3 bytes.

A3.55Practice1 mark

Noise reduction, normalisation and resizing are techniques of

Answer

(d) preprocessing They clean and prepare images: preprocessing.

A3.56Practice1 mark

Giving one label to the whole image is called

Answer

(a) image classification One label for the whole image: image classification.

A3.57Practice1 mark

The quality of a camera image is poor in fog and at night. This is a challenge of

Answer

(c) image acquisition Poor light and weather affect image acquisition.

A3.58Practice1 mark

Which stage comes just before high-level processing?

Answer

(c) Detection / Segmentation Detection/segmentation comes before high-level processing.

A3.59Practice1 mark

A colour (RGB) image has the resolution 12 x 12. How many bytes are needed to store its pixel values without compression?

Answer

(d) 432 12 x 12 pixels x 3 bytes.

A3.60Practice1 mark

An RGB image has the resolution 28 x 28. How many values (numbers) are stored for the whole image?

Answer

(a) 2,352 Each of the 784 pixels stores 3 values: red, green and blue.

A3.61Practice1 mark

Marking each separate object, even of the same class, with its own outline is

Answer

(b) instance segmentation Instance segmentation separates every object.

A3.62Practice1 mark

Removing unwanted grain and speckles from an image is called

Answer

(b) noise reduction Grain and speckles are noise; removing them is noise reduction.

A3.63Practice1 mark

The smallest unit of a digital image is the

Answer

(d) pixel The pixel is the smallest unit.

A3.64Practice1 mark

Making all the images the same size before giving them to a model is called

Answer

(d) resizing Resizing makes the images the same size.

A4Big data MCQ1 mark · 46 questions
A4.1SQP 2026-271 mark

Which of these is NOT a data analytics tool?

Answer

(c) MySQL MySQL is a database management system.

A4.2SQP 2026-271 mark

Which 'V' of Big Data is about the consistency and trustworthiness of the data?

Answer

(b) Veracity Veracity is about how accurate and trustworthy data is.

A4.3SQP 2026-271 mark

Which law says that computing power keeps increasing with time, which makes it easier to handle large volumes of data?

Answer

(c) Moore's Law Moore's Law: transistors on a chip (computing power) double about every two years.

A4.4Practice1 mark

A sensor produces 2 MB of data every second. How much data does it produce in one minute?

Answer

(d) 120 MB 2 x 60.

A4.5Practice1 mark

Which unit comes just after the petabyte (PB)?

Answer

(b) Exabyte (EB) KB < MB < GB < TB < PB < EB: the exabyte comes after PB.

A4.6Practice1 mark

Getting insights from data at the moment it arrives, so that decisions are immediate, is called

Answer

(c) real-time analytics Real-time analytics works on data as it arrives.

A4.7Practice1 mark

Which tool makes interactive dashboards and charts from data?

Answer

(b) Tableau Tableau builds interactive dashboards.

A4.8Practice1 mark

A CCTV camera stores 4 GB of video every day. How much does it store in 30 days?

Answer

(a) 120 GB 4 x 30.

A4.9Practice1 mark

1 GB is equal to how many MB?

Answer

(d) 1,024 Each bigger unit is 1,024 times the smaller one.

A4.10Practice1 mark

Which of these is an advantage of Big Data?

Answer

(b) Better decision making More data gives better decisions.

A4.11Practice1 mark

Data stored in rows and columns, such as an SQL table, is

Answer

(b) structured data Rows and columns with a fixed format is structured data.

A4.12Practice1 mark

Changes in the meaning or flow of data with time is the V called

Answer

(b) Variability Variability is the change in meaning or flow of data.

A4.13Practice1 mark

1 PB is equal to how many GB?

Answer

(a) 1,048,576 1 PB = 1,024 TB and 1 TB = 1,024 GB.

A4.14Practice1 mark

Readings sent every second by the sensors of a smart watch are an example of

Answer

(c) a data stream Continuous readings form a data stream.

A4.15Practice1 mark

A feedback form with name, age and rating in fixed columns is

Answer

(b) structured data Fixed fields make it structured data.

A4.16Practice1 mark

How many gigabytes are there in 3 TB?

Answer

(d) 3,072 3 x 1,024.

A4.17Practice1 mark

Which is the first step in the working of Big Data analytics?

Answer

(a) Gather data First gather the data.

A4.18Practice1 mark

Customer details and transaction records kept in the tables of a database are

Answer

(c) structured data Database tables hold structured data.

A4.19Practice1 mark

The 3 Vs of Big Data are

Answer

(a) Volume, Velocity and Variety Volume, Velocity and Variety.

A4.20Practice1 mark

1 MB is equal to how many KB?

Answer

(d) 1,024 Each bigger unit is 1,024 times the smaller one.

A4.21Practice1 mark

Which 'V' is shown when a bank processes thousands of card payments every second?

Answer

(d) Velocity Speed of data is Velocity.

A4.22Practice1 mark

Which of these is the largest unit of data?

Answer

(b) Zettabyte KB, MB, GB, TB, PB, EB, ZB: each is 1,024 times the one before.

A4.23Practice1 mark

1 PB is equal to how many TB?

Answer

(d) 1,024 Each bigger unit is 1,024 times the smaller one.

A4.24Practice1 mark

How many megabytes are there in 5 GB?

Answer

(b) 5,120 5 x 1,024.

A4.25Practice1 mark

Which of these is a NoSQL database used for Big Data?

Answer

(d) MongoDB MongoDB is a NoSQL (document) database.

A4.26Practice1 mark

Data that arrives continuously and at high speed, such as sensor readings, is called a

Answer

(b) data stream A continuous flow of data is a data stream.

A4.27Practice1 mark

Removing errors and duplicates from the data is done in the step

Answer

(a) Clean data Cleaning removes errors and duplicates.

A4.28Practice1 mark

Data that is too large and complex for traditional tools to handle is called

Answer

(b) Big Data That is Big Data.

A4.29Practice1 mark

An app gets 500 new records every second. How many records does it get in one minute?

Answer

(a) 30,000 500 x 60.

A4.30Practice1 mark

Which 'V' is weak when a data set has many fake and duplicate entries?

Answer

(d) Veracity Fake and duplicate entries make data less trustworthy: Veracity.

A4.31Practice1 mark

Images, videos and audio files are examples of

Answer

(c) unstructured data They have no fixed rows and columns: unstructured data.

A4.32Practice1 mark

XML and JSON files are examples of

Answer

(c) semi-structured data They have tags/keys but no fixed table: semi-structured data.

A4.33Practice1 mark

The huge amount of data produced every second is

Answer

(b) Volume Volume is the amount of data.

A4.34Practice1 mark

1 TB is equal to how many GB?

Answer

(d) 1,024 Each bigger unit is 1,024 times the smaller one.

A4.35Practice1 mark

Posts, photos and videos on social media are mostly

Answer

(b) unstructured data Free-form posts and media are unstructured.

A4.36Practice1 mark

The speed at which data is produced and processed is

Answer

(a) Velocity Velocity is the speed of data.

A4.37Practice1 mark

Which is the correct order from the smallest to the largest?

Answer

(a) GB, TB, PB, EB GB < TB < PB < EB, each 1024 times the previous.

A4.38Practice1 mark

Data mining, predictive analytics and deep learning are used in the step

Answer

(a) Analyse data They find insights, so they are used in Analyse data.

A4.39Practice1 mark

In which step of Big Data analytics is the data organised so that queries give correct results?

Answer

(b) Process data Process data organises and structures the data.

A4.40Practice1 mark

Extracting useful information from a continuous flow of data is called

Answer

(b) mining data streams Mining data streams finds information in flowing data.

A4.41Practice1 mark

The usefulness of data for a business is

Answer

(a) Value Value is the usefulness of data.

A4.42Practice1 mark

Data coming as text, images, audio and video shows

Answer

(c) Variety Many forms of data show Variety.

A4.43Practice1 mark

Which is the correct order of the working of Big Data analytics?

Answer

(d) Gather, Process, Clean, Analyse Gather → Process → Clean → Analyse.

A4.44Practice1 mark

Which of these is a tool for Big Data?

Answer

(b) Apache Hadoop Apache Hadoop stores and processes big data across many computers.

A4.45Practice1 mark

Which unit comes just after the terabyte (TB)?

Answer

(b) Petabyte (PB) After TB comes the petabyte (PB).

A4.46Practice1 mark

Which of these is a disadvantage of Big Data?

Answer

(d) Risk to privacy and security Large personal data can be leaked or misused: privacy risk.

A5Neural networks MCQ, with numericals1 mark · 68 questions
A5.1SQP 2026-271 mark

A neural network with two or more hidden layers is called a

Answer

(d) deep neural network Two or more hidden layers make it deep.

A5.2SQP 2026-271 mark

Another name for a perceptron is

Answer

(d) standard neural network A perceptron is the simplest (standard) neural network.

A5.3SQP 2026-271 mark

Which loss function is NOT used for regression?

Answer

(a) Log loss (binary cross-entropy) Log loss (cross-entropy) is for classification; MSE and MAE are for regression.

A5.4SQP 2026-271 mark

Which of these is an activation function?

Answer

(c) ReLU ReLU (also sigmoid, tanh) is an activation function.

A5.5SQP 2026-271 mark

In the formula output = (w x input) + b, the terms w and b are called

Answer

(c) weight and bias w is the weight and b is the bias.

A5.6Practice1 mark

Which type of neural network is best for images?

Answer

(a) Convolutional Neural Network (CNN) CNNs use convolution to find image features.

A5.7Practice1 mark

A neuron has the inputs 3 and 3 with the weights 1 and -2, and the bias -3. What is its output with the ReLU activation function?

Answer

(a) 0 Weighted sum = (3 x 1) + (3 x -2) + (-3) = -6. ReLU gives max(0, -6) = 0.

A5.8Practice1 mark

Weighted sum of a neuron =

Answer

(c) sum of (input x weight) + bias Each input is multiplied by its weight, added up, and the bias is added.

A5.9Practice1 mark

The output of the sigmoid function lies between

Answer

(a) 0 and 1 Sigmoid squeezes any value into 0 to 1.

A5.10Practice1 mark

The activation function is needed because it

Answer

(b) adds non-linearity, so the network can learn complex patterns Without it the network would be only linear and could not learn complex patterns.

A5.11Practice1 mark

What is the output of the ReLU activation function for the input -2?

Answer

(c) 0 ReLU(x) = max(0, x): a negative input gives 0, a positive input comes out unchanged.

A5.12Practice1 mark

Passing the input through the layers to get the output is called

Answer

(c) forward propagation Moving forward from input to output is forward propagation.

A5.13Practice1 mark

A neuron has the inputs x1 = 2 with weight w1 = -1, x2 = 3 with weight w2 = 1, x3 = 2 with weight w3 = 1. The bias is -1. What is the weighted sum (with bias)?

Answer

(b) 2 Weighted sum = (2 x -1) + (3 x 1) + (2 x 1) + (-1) = 2.

A5.14Practice1 mark

A neuron has the inputs x1 = 3 with weight w1 = -1, x2 = 0 with weight w2 = 1. The bias is -1. What is the weighted sum (with bias)?

Answer

(c) -4 Weighted sum = (3 x -1) + (0 x 1) + (-1) = -4.

A5.15Practice1 mark

A neuron has the inputs x1 = 5 with weight w1 = -2, x2 = 1 with weight w2 = -1, x3 = 2 with weight w3 = 4. The bias is -2. What is the weighted sum (with bias)?

Answer

(b) -5 Weighted sum = (5 x -2) + (1 x -1) + (2 x 4) + (-2) = -5.

A5.16Practice1 mark

What is the output of the ReLU activation function for the input 7?

Answer

(a) 7 ReLU(x) = max(0, x): a negative input gives 0, a positive input comes out unchanged.

A5.17Practice1 mark

The layers between the input layer and the output layer are called

Answer

(a) hidden layers They are hidden layers.

A5.18Practice1 mark

Which Python library is used to build and train neural networks?

Answer

(a) TensorFlow TensorFlow (with Keras) builds and trains neural networks.

A5.19Practice1 mark

A neuron has the inputs x1 = 2 with weight w1 = 2, x2 = 2 with weight w2 = 3. The bias is 1. What is the weighted sum (with bias)?

Answer

(b) 11 Weighted sum = (2 x 2) + (2 x 3) + (1) = 11.

A5.20Practice1 mark

What is the output of the ReLU activation function for the input -5?

Answer

(d) 0 ReLU(x) = max(0, x): a negative input gives 0, a positive input comes out unchanged.

A5.21Practice1 mark

A GAN has two networks. They are the

Answer

(d) generator and discriminator A GAN has a generator and a discriminator.

A5.22Practice1 mark

What is the output of the ReLU activation function for the input 12?

Answer

(a) 12 ReLU(x) = max(0, x): a negative input gives 0, a positive input comes out unchanged.

A5.23Practice1 mark

Which activation function gives values between 0 and 1 and is used for probability?

Answer

(d) Sigmoid Sigmoid output (0 to 1) can be read as a probability.

A5.24Practice1 mark

A neuron has the inputs x1 = 0 with weight w1 = 4, x2 = 4 with weight w2 = 2. The bias is -1. What is the weighted sum (with bias)?

Answer

(b) 7 Weighted sum = (0 x 4) + (4 x 2) + (-1) = 7.

A5.25Practice1 mark

Which type of neural network is best for sequence data such as text and speech?

Answer

(b) Recurrent Neural Network (RNN) RNNs remember earlier inputs, so they suit sequences.

A5.26Practice1 mark

A neuron has the inputs x1 = 1 with weight w1 = 3, x2 = 0 with weight w2 = -1, x3 = 0 with weight w3 = 1. The bias is 1. What is the weighted sum (with bias)?

Answer

(c) 4 Weighted sum = (1 x 3) + (0 x -1) + (0 x 1) + (1) = 4.

A5.27Practice1 mark

An input layer of 6 neurons is fully connected to a hidden layer of 3 neurons. How many weights are there between the two layers?

Answer

(b) 18 Every input neuron is joined to every hidden neuron: 6 x 3.

A5.28Practice1 mark

Which type of network is used in voice assistants to process speech?

Answer

(a) Recurrent Neural Network Speech is a sequence, so RNNs are used.

A5.29Practice1 mark

A neuron has the inputs x1 = 1 with weight w1 = 4, x2 = 3 with weight w2 = 1, x3 = 1 with weight w3 = 4. The bias is -2. What is the weighted sum (with bias)?

Answer

(c) 9 Weighted sum = (1 x 4) + (3 x 1) + (1 x 4) + (-2) = 9.

A5.30Practice1 mark

Which layer gives the final prediction?

Answer

(c) Output layer The output layer gives the result.

A5.31Practice1 mark

A neuron has the inputs x1 = 2 with weight w1 = -2, x2 = 3 with weight w2 = 3 and bias -2. It gives the output 1 if the weighted sum is 5 or more, otherwise 0. What is the output?

Answer

(b) 0 Weighted sum = (2 x -2) + (3 x 3) + (-2) = 3. It is less than the threshold 5.

A5.32Practice1 mark

A learning rate that is too large makes the training

Answer

(a) unstable: the loss may jump and not settle Too large steps overshoot, so the loss jumps around.

A5.33Practice1 mark

Which tool lets you see a neural network learn in the browser?

Answer

(c) TensorFlow Playground TensorFlow Playground shows a network learning live in the browser.

A5.34Practice1 mark

A neuron has the inputs x1 = 0 with weight w1 = 3, x2 = 1 with weight w2 = 1. The bias is 1. What is the weighted sum (with bias)?

Answer

(b) 2 Weighted sum = (0 x 3) + (1 x 1) + (1) = 2.

A5.35Practice1 mark

A neuron has the inputs x1 = 5 with weight w1 = 2, x2 = 4 with weight w2 = 4 and bias 3. It gives the output 1 if the weighted sum is 30 or more, otherwise 0. What is the output?

Answer

(a) 0 Weighted sum = (5 x 2) + (4 x 4) + (3) = 29. It is less than the threshold 30.

A5.36Practice1 mark

The ReLU function gives the output

Answer

(b) 0 for a negative input and the input itself for a positive input ReLU(x) = max(0, x): 0 for negatives, x for positives.

A5.37Practice1 mark

The function that measures the difference between the predicted and the actual output is the

Answer

(b) loss function The loss function measures the error.

A5.38Practice1 mark

A network in which data moves only in one direction, from input to output, is a

Answer

(b) feed-forward neural network One-way flow: feed-forward neural network.

A5.39Practice1 mark

An input layer of 2 neurons is fully connected to a hidden layer of 3 neurons. How many weights are there between the two layers?

Answer

(b) 6 Every input neuron is joined to every hidden neuron: 2 x 3.

A5.40Practice1 mark

Which loss function is used for a two-class classification problem?

Answer

(a) Binary cross-entropy (log loss) Binary cross-entropy (log loss) is used for two classes.

A5.41Practice1 mark

A neuron has the inputs 2 and 4 with the weights 1 and -1, and the bias -5. What is its output with the ReLU activation function?

Answer

(d) 0 Weighted sum = (2 x 1) + (4 x -1) + (-5) = -7. ReLU gives max(0, -7) = 0.

A5.42Practice1 mark

The method used to reduce the loss by changing the weights step by step is

Answer

(b) gradient descent Gradient descent moves the weights downhill on the loss.

A5.43Practice1 mark

One complete pass of the whole training data through the network is called an

Answer

(a) epoch One full pass is an epoch.

A5.44Practice1 mark

A neuron has the inputs 1 and 3 with the weights 2 and 1, and the bias -5. What is its output with the ReLU activation function?

Answer

(b) 0 Weighted sum = (1 x 2) + (3 x 1) + (-5) = 0. ReLU gives max(0, 0) = 0.

A5.45Practice1 mark

An input layer of 4 neurons is fully connected to a hidden layer of 4 neurons. How many weights are there between the two layers?

Answer

(a) 16 Every input neuron is joined to every hidden neuron: 4 x 4.

A5.46Practice1 mark

The basic unit of a neural network is the

Answer

(d) neuron (node) The neuron (node) is the basic unit.

A5.47Practice1 mark

Sending the error backwards to adjust the weights is called

Answer

(b) backpropagation Backpropagation sends the error back to update the weights.

A5.48Practice1 mark

What is the output of the ReLU activation function for the input -9?

Answer

(c) 0 ReLU(x) = max(0, x): a negative input gives 0, a positive input comes out unchanged.

A5.49Practice1 mark

A neuron has the inputs x1 = 3 with weight w1 = -2, x2 = 0 with weight w2 = -1, x3 = 5 with weight w3 = -2 and bias 1. It gives the output 1 if the weighted sum is -16 or more, otherwise 0. What is the output?

Answer

(d) 1 Weighted sum = (3 x -2) + (0 x -1) + (5 x -2) + (1) = -15. It is not less than the threshold -16.

A5.50Practice1 mark

A neuron has the inputs 3 and 2 with the weights 1 and -1, and the bias 2. What is its output with the ReLU activation function?

Answer

(a) 3 Weighted sum = (3 x 1) + (2 x -1) + (2) = 3. ReLU gives max(0, 3) = 3.

A5.51Practice1 mark

A neuron has the inputs 3 and 1 with the weights 3 and 2, and the bias -5. What is its output with the ReLU activation function?

Answer

(a) 6 Weighted sum = (3 x 3) + (1 x 2) + (-5) = 6. ReLU gives max(0, 6) = 6.

A5.52Practice1 mark

A neuron has the inputs 3 and 3 with the weights -1 and -1, and the bias -3. What is its output with the ReLU activation function?

Answer

(a) 0 Weighted sum = (3 x -1) + (3 x -1) + (-3) = -9. ReLU gives max(0, -9) = 0.

A5.53Practice1 mark

A neuron has the inputs 4 and 2 with the weights -1 and 2, and the bias -3. What is its output with the ReLU activation function?

Answer

(b) 0 Weighted sum = (4 x -1) + (2 x 2) + (-3) = -3. ReLU gives max(0, -3) = 0.

A5.54Practice1 mark

Which layer of a neural network receives the data?

Answer

(b) Input layer The input layer receives the data.

A5.55Practice1 mark

The number that shows the strength of a connection between two neurons is the

Answer

(b) weight The weight shows the strength of a connection.

A5.56Practice1 mark

During training, which values of a neural network are adjusted?

Answer

(a) Weights and biases Training adjusts the weights and biases.

A5.57Practice1 mark

What is the output of the ReLU activation function for the input 0?

Answer

(b) 0 ReLU(x) = max(0, x): a negative input gives 0, a positive input comes out unchanged.

A5.58Practice1 mark

A neuron has the inputs 1 and 3 with the weights -3 and 1, and the bias -1. What is its output with the ReLU activation function?

Answer

(d) 0 Weighted sum = (1 x -3) + (3 x 1) + (-1) = -1. ReLU gives max(0, -1) = 0.

A5.59Practice1 mark

A neuron has the inputs 1 and 4 with the weights -3 and -2, and the bias 1. What is its output with the ReLU activation function?

Answer

(c) 0 Weighted sum = (1 x -3) + (4 x -2) + (1) = -10. ReLU gives max(0, -10) = 0.

A5.60Practice1 mark

An input layer of 4 neurons is fully connected to a hidden layer of 5 neurons. How many weights are there between the two layers?

Answer

(c) 20 Every input neuron is joined to every hidden neuron: 4 x 5.

A5.61Practice1 mark

The output of the tanh function lies between

Answer

(c) -1 and 1 tanh gives values from -1 to 1.

A5.62Practice1 mark

A neuron has the inputs 3 and 2 with the weights -2 and -2, and the bias 2. What is its output with the ReLU activation function?

Answer

(d) 0 Weighted sum = (3 x -2) + (2 x -2) + (2) = -8. ReLU gives max(0, -8) = 0.

A5.63Practice1 mark

An input layer of 5 neurons is fully connected to a hidden layer of 2 neurons. How many weights are there between the two layers?

Answer

(c) 10 Every input neuron is joined to every hidden neuron: 5 x 2.

A5.64Practice1 mark

A neuron has the inputs x1 = 0 with weight w1 = -2, x2 = 3 with weight w2 = 4. The bias is -3. What is the weighted sum (with bias)?

Answer

(b) 9 Weighted sum = (0 x -2) + (3 x 4) + (-3) = 9.

A5.65Practice1 mark

An input layer of 3 neurons is fully connected to a hidden layer of 4 neurons. How many weights are there between the two layers?

Answer

(c) 12 Every input neuron is joined to every hidden neuron: 3 x 4.

A5.66Practice1 mark

A neuron has the inputs x1 = 5 with weight w1 = 3, x2 = 4 with weight w2 = 3, x3 = 4 with weight w3 = 4. The bias is 3. What is the weighted sum (with bias)?

Answer

(d) 46 Weighted sum = (5 x 3) + (4 x 3) + (4 x 4) + (3) = 46.

A5.67Practice1 mark

Which type of network has connections that loop back, giving it memory?

Answer

(b) Recurrent Neural Network RNNs have loops that keep earlier information.

A5.68Practice1 mark

A neuron has the inputs x1 = 0 with weight w1 = 4, x2 = 4 with weight w2 = 1, x3 = 2 with weight w3 = -1 and bias -1. It gives the output 1 if the weighted sum is 2 or more, otherwise 0. What is the output?

Answer

(d) 0 Weighted sum = (0 x 4) + (4 x 1) + (2 x -1) + (-1) = 1. It is less than the threshold 2.

A6Generative AI MCQ1 mark · 32 questions
A6.1SQP 2026-271 mark

What is the main aim of generative AI?

Answer

(a) To create new data that resembles the data it was trained on Generative AI creates new data like its training data.

A6.2SQP 2026-271 mark

Which of these tools is NOT used to generate images?

Answer

(a) Google Lumiere Lumiere generates videos.

A6.3SQP 2026-271 mark

A student submits an essay written by an AI tool as his own work. This is

Answer

(a) plagiarism Presenting AI-written work as your own is plagiarism.

A6.4Practice1 mark

A model that learns the boundary between classes, such as 'cat' and 'dog', is a

Answer

(c) discriminative model A discriminative model separates classes.

A6.5Practice1 mark

A model that learns how the data is distributed and can produce new samples is a

Answer

(b) generative model A generative model can create new samples.

A6.6Practice1 mark

LLM stands for

Answer

(d) Large Language Model LLM = Large Language Model.

A6.7Practice1 mark

Which of these is a Large Language Model?

Answer

(c) GPT GPT is a large language model.

A6.8Practice1 mark

In a GAN, the network that creates fake samples is the

Answer

(c) generator The generator creates fake samples.

A6.9Practice1 mark

In a GAN, the network that checks whether a sample is real or fake is the

Answer

(c) discriminator The discriminator judges real or fake.

A6.10Practice1 mark

A VAE has two parts. They are the

Answer

(c) encoder and decoder A VAE has an encoder and a decoder.

A6.11Practice1 mark

VAE stands for

Answer

(a) Variational Autoencoder VAE = Variational Autoencoder.

A6.12Practice1 mark

A realistic fake video or audio of a person made with AI is called a

Answer

(c) deepfake That is a deepfake.

A6.13Practice1 mark

Writing a clear instruction to get the desired output from a generative AI tool is called

Answer

(b) prompt engineering Prompt engineering means writing good prompts.

A6.14Practice1 mark

Which tool generates text answers to prompts?

Answer

(d) ChatGPT ChatGPT answers prompts with text.

A6.15Practice1 mark

When an LLM gives a confident but wrong or made-up answer, it is called

Answer

(b) hallucination Made-up confident answers are hallucinations.

A6.16Practice1 mark

Which of these is an ethical concern of generative AI?

Answer

(c) Bias in the generated content Generated content can be biased.

A6.17Practice1 mark

Which of these is a limitation of LLMs?

Answer

(a) They need very high processing power LLMs need very high computing power.

A6.18Practice1 mark

Which tool can generate a presentation design or image from a text prompt?

Answer

(c) Canva Canva has AI features that design from a text prompt.

A6.19Practice1 mark

Which of these is an application of generative AI in audio?

Answer

(b) Creating music or a voice from text Creating music or a voice from text is generative audio.

A6.20Practice1 mark

Who owns the content created by AI? This question is about

Answer

(b) copyright and ownership Ownership of AI content is a copyright question.

A6.21Practice1 mark

Google's large language model that can be used through an API is

Answer

(b) Gemini Gemini is Google's LLM.

A6.22Practice1 mark

Which of these is a responsible use of generative AI?

Answer

(b) Checking the facts and telling that AI was used Check facts and say that AI was used.

A6.23Practice1 mark

Which of these is a discriminative task?

Answer

(b) Classifying an e-mail as spam or not spam Spam or not spam is classification: discriminative.

A6.24Practice1 mark

Which of these is a generative task?

Answer

(b) Creating a new image of a landscape Creating a new image is generative.

A6.25Practice1 mark

In a VAE, the part that compresses the input into a small code is the

Answer

(b) encoder The encoder compresses the input.

A6.26Practice1 mark

In a VAE, the part that produces data from the code is the

Answer

(c) decoder The decoder rebuilds data from the code.

A6.27Practice1 mark

Which tool generates images from a text prompt?

Answer

(d) DALL-E DALL-E makes images from text.

A6.28Practice1 mark

LLMs are trained mainly on

Answer

(c) huge amounts of text LLMs learn from huge amounts of text.

A6.29Practice1 mark

Which is the best prompt?

Answer

(d) Write a 100-word note on Big Data for Class XII with one example A good prompt is clear and specific.

A6.30Practice1 mark

An AI system that gives lower loan scores to one group because of its training data shows

Answer

(c) bias Unfair results from data show bias.

A6.31Practice1 mark

Which of these is a text-to-video tool?

Answer

(c) Google Lumiere Google Lumiere generates video from text.

A6.32Practice1 mark

Using generative AI to copy a singer's voice without permission raises the issue of

Answer

(a) consent and copyright It needs the singer's consent and respects copyright.

A7Data storytelling MCQ1 mark · 32 questions
A7.1SQP 2026-271 mark

Which narrative structure is used to present a data story with an introduction, rising action, climax, falling action and conclusion?

Answer

(a) Freytag's Pyramid Freytag's Pyramid has these five parts.

A7.2SQP 2026-271 mark

Which visualisation uses colour to compare categories?

Answer

(b) Heat map A heat map shows values with colours.

A7.3SQP 2026-271 mark

Which statement about stories is NOT true?

Answer

(a) Stories are harder to remember than plain numbers Stories are EASIER to remember than plain numbers.

A7.4Practice1 mark

The three key elements of data storytelling are

Answer

(c) data, narrative and visuals Data, narrative and visuals.

A7.5Practice1 mark

Data together with a narrative helps to

Answer

(a) explain what is happening in the data A narrative explains what the data shows.

A7.6Practice1 mark

Data together with visuals helps to

Answer

(b) enlighten the audience by showing patterns they would not see otherwise Visuals enlighten: they show patterns hidden in numbers.

A7.7Practice1 mark

A narrative together with visuals helps to

Answer

(a) engage the audience A story with visuals engages the audience.

A7.8Practice1 mark

When data, narrative and visuals are combined well, the data story can

Answer

(d) influence and drive change All three together influence decisions and drive change.

A7.9Practice1 mark

Which is the first stage of Freytag's Pyramid?

Answer

(b) Introduction It begins with the Introduction (exposition).

A7.10Practice1 mark

The most important finding of a data story is placed at the

Answer

(c) climax The climax carries the key insight.

A7.11Practice1 mark

Which is the last stage of Freytag's Pyramid?

Answer

(c) Conclusion It ends with the Conclusion (resolution).

A7.12Practice1 mark

Which visualisation is best for text data, to show the most frequent words?

Answer

(b) Word cloud A word cloud shows frequent words larger.

A7.13Practice1 mark

Which visualisation is best to show a trend of numeric data over time?

Answer

(d) Line graph A line graph shows trends over time.

A7.14Practice1 mark

Which visualisation is used for stock prices?

Answer

(a) Candlestick chart Candlestick charts show open, high, low and close prices.

A7.15Practice1 mark

Which visualisation is best for data of different places?

Answer

(c) Map A map shows data by location.

A7.16Practice1 mark

Showing data in the form of charts and graphs is called

Answer

(d) data visualisation That is data visualisation.

A7.17Practice1 mark

Which is the first step in creating a data story?

Answer

(d) Collect the data and organise it First collect and organise the data.

A7.18Practice1 mark

Changing the scale of a graph to mislead the audience is

Answer

(b) unethical Misleading graphs are unethical.

A7.19Practice1 mark

A data story is more effective than a table of numbers because

Answer

(d) people remember stories better than numbers People remember stories better than numbers.

A7.20Practice1 mark

Before making a data story, we must first know

Answer

(a) who the audience is Know your audience first.

A7.21Practice1 mark

Which chart shows many small charts of the same kind for different groups (mixed data)?

Answer

(c) Facet grid A facet grid shows small multiples for each group.

A7.22Practice1 mark

In Freytag's Pyramid, the part that builds interest by showing the problem in the data is the

Answer

(c) rising action Rising action builds interest by showing the problem.

A7.23Practice1 mark

In a data story, the 'conflict' is

Answer

(b) the problem shown by the data The conflict is the problem the data shows.

A7.24Practice1 mark

The stage of Freytag's Pyramid that comes just after the climax is

Answer

(d) falling action After the climax comes the falling action.

A7.25Practice1 mark

Which element of data storytelling gives the facts?

Answer

(a) Data Data gives the facts.

A7.26Practice1 mark

Which element of data storytelling gives the storyline and meaning?

Answer

(c) Narrative The narrative gives meaning.

A7.27Practice1 mark

Which chart is best to show the share of each category in a whole?

Answer

(a) Pie chart A pie chart shows parts of a whole.

A7.28Practice1 mark

Which chart is best to compare the sales of five products?

Answer

(c) Bar chart A bar chart compares categories.

A7.29Practice1 mark

In a word cloud, a bigger word means that the word

Answer

(a) occurs more often Bigger words occur more often.

A7.30Practice1 mark

Showing only the data that supports your view and hiding the rest is

Answer

(c) unethical (cherry-picking) Cherry-picking data is unethical.

A7.31Practice1 mark

The setting and the characters of a data story are given in the

Answer

(a) introduction The introduction sets the scene.

A7.32Practice1 mark

A data story should end with

Answer

(b) a clear conclusion or call to action End with a clear conclusion or call to action.

A8True or False: two statements1 mark · 50 questions
A8.1Practice1 mark

Statement 1: The Data Science Methodology has ten steps.

Statement 2: Feedback is its last step.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.2Practice1 mark

Statement 1: Business Understanding is the first step of the methodology.

Statement 2: Deployment comes before Modelling.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.3Practice1 mark

Statement 1: MSE can be negative.

Statement 2: RMSE is the square root of MSE.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A8.4Practice1 mark

Statement 1: Feature engineering uses domain knowledge to create new features from raw data.

Statement 2: Feature engineering is done in the Feedback step.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.5Practice1 mark

Statement 1: Precision and recall are metrics for regression.

Statement 2: RMSE is a metric for classification.

Answer

(b) Both the statements are false. Statement 1 is false; Statement 2 is false.

A8.6Practice1 mark

Statement 1: In k-fold cross validation, every fold is used once as the test set.

Statement 2: Cross validation takes more computing time than one train-test split.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.7Practice1 mark

Statement 1: Image acquisition is the first stage of the computer vision process.

Statement 2: High-level processing is the last stage.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.8Practice1 mark

Statement 1: Noise reduction is a preprocessing technique.

Statement 2: Edge detection is a preprocessing technique.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.9Practice1 mark

Statement 1: A higher resolution image has fewer pixels.

Statement 2: A grayscale image has three channels.

Answer

(b) Both the statements are false. Statement 1 is false; Statement 2 is false.

A8.10Practice1 mark

Statement 1: Object detection can find many objects in one image.

Statement 2: Image classification gives a box for every object.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.11Practice1 mark

Statement 1: Instance segmentation separates two objects of the same class.

Statement 2: Semantic segmentation labels every pixel with a class.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.12Practice1 mark

Statement 1: Veracity is about the trustworthiness of data.

Statement 2: Velocity is about the speed of data.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.13Practice1 mark

Statement 1: JSON is an example of unstructured data.

Statement 2: A video file is an example of unstructured data.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A8.14Practice1 mark

Statement 1: Volume is about the huge amount of data.

Statement 2: Variety means that all the data is of one type.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.15Practice1 mark

Statement 1: MySQL is a Big Data analytics tool.

Statement 2: The first step of Big Data analytics is to analyse the data.

Answer

(b) Both the statements are false. Statement 1 is false; Statement 2 is false.

A8.16Practice1 mark

Statement 1: Big Data can help a business to take better decisions.

Statement 2: Big Data has no risk to privacy.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.17Practice1 mark

Statement 1: A deep neural network has two or more hidden layers.

Statement 2: A perceptron is also called a standard neural network.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.18Practice1 mark

Statement 1: ReLU gives 0 for a negative input.

Statement 2: The sigmoid function gives values between -1 and 1.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.19Practice1 mark

Statement 1: Backpropagation adjusts the weights using the error.

Statement 2: Forward propagation moves from the output layer to the input layer.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.20Practice1 mark

Statement 1: CNNs are mostly used for image data.

Statement 2: RNNs are mostly used for sequence data.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.21Practice1 mark

Statement 1: Bias is the layer that gives the final output.

Statement 2: Weights are fixed and never change during training.

Answer

(b) Both the statements are false. Statement 1 is false; Statement 2 is false.

A8.22Practice1 mark

Statement 1: Log loss is used for regression.

Statement 2: MSE is a loss function for regression.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A8.23Practice1 mark

Statement 1: Generative AI creates new content.

Statement 2: A discriminative model creates new images.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.24Practice1 mark

Statement 1: A GAN has a generator and a discriminator.

Statement 2: A VAE has an encoder and a decoder.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.25Practice1 mark

Statement 1: LLMs never make mistakes.

Statement 2: LLMs need no training data.

Answer

(b) Both the statements are false. Statement 1 is false; Statement 2 is false.

A8.26Practice1 mark

Statement 1: A deepfake is a real video recorded by a camera.

Statement 2: Deepfakes can be used to spread false information.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A8.27Practice1 mark

Statement 1: Submitting AI-written work as your own is plagiarism.

Statement 2: Generated content can carry the bias of the training data.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.28Practice1 mark

Statement 1: Data, narrative and visuals are the three elements of data storytelling.

Statement 2: A word cloud is used for text data.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.29Practice1 mark

Statement 1: The climax is the first stage of Freytag's Pyramid.

Statement 2: The conclusion is the last stage of Freytag's Pyramid.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A8.30Practice1 mark

Statement 1: A heat map uses colour to show values.

Statement 2: A candlestick chart is used for text data.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.31Practice1 mark

Statement 1: Stories are harder to remember than numbers.

Statement 2: A data story needs no data.

Answer

(b) Both the statements are false. Statement 1 is false; Statement 2 is false.

A8.32Practice1 mark

Statement 1: A line graph shows a trend over time.

Statement 2: The audience should be kept in mind while making a data story.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.33Practice1 mark

Statement 1: Analytic Approach is the second step of the methodology.

Statement 2: Data Collection comes before Data Requirements.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.34Practice1 mark

Statement 1: A predictive approach answers 'What will happen?'

Statement 2: A diagnostic approach answers 'Why did it happen?'

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.35Practice1 mark

Statement 1: A smaller RMSE means a better regression model.

Statement 2: Accuracy is a metric for regression.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.36Practice1 mark

Statement 1: Feature extraction comes after preprocessing.

Statement 2: Image acquisition is done with cameras and sensors.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.37Practice1 mark

Statement 1: Histogram equalisation improves the contrast of an image.

Statement 2: Normalisation is a feature extraction technique.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.38Practice1 mark

Statement 1: The pixel value 0 means white in a grayscale image.

Statement 2: An RGB pixel stores three values.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A8.39Practice1 mark

Statement 1: A spreadsheet of marks is structured data.

Statement 2: An e-mail with attachments is fully structured data.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.40Practice1 mark

Statement 1: Hadoop and Spark are tools for Big Data.

Statement 2: Cleaning the data removes errors and duplicates.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.41Practice1 mark

Statement 1: Value is about the usefulness of data.

Statement 2: Velocity is about the trustworthiness of data.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.42Practice1 mark

Statement 1: The input layer receives the data.

Statement 2: The output layer gives the final prediction.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.43Practice1 mark

Statement 1: The sigmoid function gives values between 0 and 1.

Statement 2: tanh gives values between 0 and 255.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.44Practice1 mark

Statement 1: Gradient descent is used to reduce the loss.

Statement 2: A loss function measures how correct the hardware is.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.45Practice1 mark

Statement 1: GPT and Gemini are large language models.

Statement 2: DALL-E is used mainly to generate images.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.46Practice1 mark

Statement 1: A discriminative model learns the boundary between classes.

Statement 2: The discriminator of a GAN creates the fake samples.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.47Practice1 mark

Statement 1: Prompt engineering means writing clear prompts.

Statement 2: AI-generated content is always free from bias.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.48Practice1 mark

Statement 1: The introduction gives the setting and the characters of the story.

Statement 2: The climax carries the main insight.

Answer

(a) Both the statements are true. Statement 1 is true; Statement 2 is true.

A8.49Practice1 mark

Statement 1: A map is used for geographic data.

Statement 2: A word cloud is used for numeric trends over time.

Answer

(c) Statement 1 is true and Statement 2 is false. Statement 1 is true; Statement 2 is false.

A8.50Practice1 mark

Statement 1: Hiding data that does not support your view is ethical.

Statement 2: The source of the data should be named.

Answer

(d) Statement 1 is false and Statement 2 is true. Statement 1 is false; Statement 2 is true.

A9Assertion and Reason1 mark · 43 questions
A9.1Practice1 mark

Assertion (A): Business Understanding is the first step of the Data Science Methodology.

Reason (R): A clear problem statement decides what data and model will be needed.

Answer

(a) Both A and R are true and R is the correct explanation of A. A clear problem decides the data and model needed (R), so it comes first (A).

A9.2Practice1 mark

Assertion (A): MSE is never negative.

Reason (R): In MSE, the errors are squared before they are averaged.

Answer

(a) Both A and R are true and R is the correct explanation of A. Errors are squared (R), and squares are never negative (A).

A9.3Practice1 mark

Assertion (A): Data Preparation takes the most time in a data science project.

Reason (R): Raw data has missing values, errors and duplicates that must be handled.

Answer

(a) Both A and R are true and R is the correct explanation of A. Raw data has missing values, errors and duplicates (R), which take time to fix (A).

A9.4Practice1 mark

Assertion (A): Cross validation gives a more reliable estimate than one train-test split.

Reason (R): In k-fold cross validation, every part of the data is used for testing once.

Answer

(a) Both A and R are true and R is the correct explanation of A. Every part is used for testing once (R), so the estimate is more reliable (A).

A9.5Practice1 mark

Assertion (A): RMSE is used to evaluate a classification model.

Reason (R): RMSE is the square root of the mean of the squared errors.

Answer

(d) A is false but R is true. RMSE is for regression.

A9.6Practice1 mark

Assertion (A): Feedback is the last step of the methodology.

Reason (R): Feedback from the users is used to improve the model.

Answer

(a) Both A and R are true and R is the correct explanation of A. Feedback from users improves the model (R), closing the cycle (A).

A9.7Practice1 mark

Assertion (A): Preprocessing is done before feature extraction.

Reason (R): Clean and uniform images give better features.

Answer

(a) Both A and R are true and R is the correct explanation of A. Clean, uniform images give better features (R).

A9.8Practice1 mark

Assertion (A): A high-resolution image shows more detail.

Reason (R): A high-resolution image has more pixels.

Answer

(a) Both A and R are true and R is the correct explanation of A. More pixels (R) capture more detail (A).

A9.9Practice1 mark

Assertion (A): Image classification can tell the position of every object in an image.

Reason (R): Image classification gives one label to the whole image.

Answer

(d) A is false but R is true. A is false: classification gives only one label (R is true); detection gives positions.

A9.10Practice1 mark

Assertion (A): Computer vision raises privacy concerns.

Reason (R): Cameras can record and identify people without their consent.

Answer

(a) Both A and R are true and R is the correct explanation of A. Cameras can identify people without consent (R).

A9.11Practice1 mark

Assertion (A): An RGB image needs more storage than a grayscale image of the same size.

Reason (R): Each RGB pixel stores three values.

Answer

(a) Both A and R are true and R is the correct explanation of A. Each RGB pixel stores three values (R).

A9.12Practice1 mark

Assertion (A): Traditional databases cannot handle Big Data easily.

Reason (R): Big Data has very high volume, velocity and variety.

Answer

(a) Both A and R are true and R is the correct explanation of A. Huge volume, speed and variety (R) are too much for them (A).

A9.13Practice1 mark

Assertion (A): A video is structured data.

Reason (R): Structured data is stored in rows and columns.

Answer

(d) A is false but R is true. A is false: video is unstructured. R (structured data has rows and columns) is true.

A9.14Practice1 mark

Assertion (A): Data must be cleaned before it is analysed.

Reason (R): Errors and duplicates in data lead to wrong results.

Answer

(a) Both A and R are true and R is the correct explanation of A. Errors and duplicates give wrong results (R).

A9.15Practice1 mark

Assertion (A): Activation functions are called the decision-makers of a neural network.

Reason (R): An activation function decides whether, and how strongly, a neuron passes its signal.

Answer

(a) Both A and R are true and R is the correct explanation of A. They decide whether and how strongly a neuron fires (R).

A9.16Practice1 mark

Assertion (A): A neural network learns during training.

Reason (R): Backpropagation adjusts the weights to reduce the loss.

Answer

(a) Both A and R are true and R is the correct explanation of A. Backpropagation adjusts the weights to reduce loss (R); that is learning (A).

A9.17Practice1 mark

Assertion (A): CNNs are widely used for image recognition.

Reason (R): RNNs have loops that remember earlier inputs.

Answer

(b) Both A and R are true but R is not the correct explanation of A. Both are true, but R is about RNNs, so it does not explain A.

A9.18Practice1 mark

Assertion (A): A network with one hidden layer is a deep neural network.

Reason (R): A deep neural network has two or more hidden layers.

Answer

(d) A is false but R is true. A is false: deep needs two or more hidden layers (R is true).

A9.19Practice1 mark

Assertion (A): The ReLU function can give a negative output.

Reason (R): ReLU gives max(0, x).

Answer

(d) A is false but R is true. A is false: ReLU = max(0, x) is never negative (R is true).

A9.20Practice1 mark

Assertion (A): A loss function is needed to train a neural network.

Reason (R): The loss shows how far the prediction is from the actual value.

Answer

(a) Both A and R are true and R is the correct explanation of A. The loss shows how far off the prediction is (R), guiding training (A).

A9.21Practice1 mark

Assertion (A): Generative AI can write a poem that did not exist before.

Reason (R): A generative model learns the pattern of its training data and produces new samples.

Answer

(a) Both A and R are true and R is the correct explanation of A. It learns patterns and produces new samples (R).

A9.22Practice1 mark

Assertion (A): The answers of an LLM should be checked before use.

Reason (R): LLMs can hallucinate, that is, give wrong information confidently.

Answer

(a) Both A and R are true and R is the correct explanation of A. LLMs can hallucinate (R), so answers must be checked (A).

A9.23Practice1 mark

Assertion (A): In a GAN, the generator and the discriminator work against each other.

Reason (R): The generator tries to fool the discriminator with fake samples.

Answer

(a) Both A and R are true and R is the correct explanation of A. The generator tries to fool the discriminator (R).

A9.24Practice1 mark

Assertion (A): Deepfakes are harmless.

Reason (R): Deepfakes are AI-made fake videos, images or audio of real people.

Answer

(d) A is false but R is true. A is false: fake videos of real people can mislead and harm. R (what deepfakes are) is true.

A9.25Practice1 mark

Assertion (A): A discriminative model is used to generate new images.

Reason (R): A discriminative model learns to tell the classes apart.

Answer

(d) A is false but R is true. A is false: it only tells classes apart (R is true); generative models create images.

A9.26Practice1 mark

Assertion (A): A data story is easier to remember than a table of numbers.

Reason (R): Stories connect the facts with emotions.

Answer

(a) Both A and R are true and R is the correct explanation of A. Stories connect facts with emotions (R).

A9.27Practice1 mark

Assertion (A): Visuals are an important element of data storytelling.

Reason (R): Charts show patterns and outliers that are hard to see in raw numbers.

Answer

(a) Both A and R are true and R is the correct explanation of A. Charts show patterns and outliers hidden in numbers (R).

A9.28Practice1 mark

Assertion (A): Freytag's Pyramid is used to structure a data story.

Reason (R): It arranges the story as introduction, rising action, climax, falling action and conclusion.

Answer

(a) Both A and R are true and R is the correct explanation of A. It arranges the story in five stages (R).

A9.29Practice1 mark

Assertion (A): A word cloud is the best chart for stock prices.

Reason (R): A word cloud shows the frequency of words.

Answer

(d) A is false but R is true. A is false: word clouds show word frequency (R is true); stock prices use candlestick or line charts.

A9.30Practice1 mark

Assertion (A): The same data story suits every audience.

Reason (R): A data story should be made keeping the audience in mind.

Answer

(d) A is false but R is true. A is false: a story must suit its audience (R is true).

A9.31Practice1 mark

Assertion (A): The analytic approach is chosen after the business problem is understood.

Reason (R): The type of question decides whether a descriptive, diagnostic, predictive or prescriptive approach is needed.

Answer

(a) Both A and R are true and R is the correct explanation of A. The type of question decides the approach (R).

A9.32Practice1 mark

Assertion (A): Accuracy alone is enough to judge every classification model.

Reason (R): When classes are unequal, precision and recall are also needed.

Answer

(d) A is false but R is true. A is false: with unequal classes, precision and recall are also needed (R is true).

A9.33Practice1 mark

Assertion (A): Noise reduction is done in the preprocessing stage.

Reason (R): Noise can hide the real features of an image.

Answer

(a) Both A and R are true and R is the correct explanation of A. Noise hides real features (R), so it is removed while preprocessing (A).

A9.34Practice1 mark

Assertion (A): Semantic segmentation and instance segmentation are the same.

Reason (R): Instance segmentation separates each object of the same class.

Answer

(d) A is false but R is true. A is false: instance segmentation separates each object of a class (R is true).

A9.35Practice1 mark

Assertion (A): Edge detection is a feature extraction technique.

Reason (R): Edges mark the boundaries of objects in an image.

Answer

(a) Both A and R are true and R is the correct explanation of A. Edges mark object boundaries (R), an important feature (A).

A9.36Practice1 mark

Assertion (A): A deep neural network can learn complex patterns.

Reason (R): It has many hidden layers that learn features step by step.

Answer

(a) Both A and R are true and R is the correct explanation of A. Many hidden layers learn features step by step (R).

A9.37Practice1 mark

Assertion (A): Weights are not changed during training.

Reason (R): Backpropagation adjusts the weights to reduce the error.

Answer

(d) A is false but R is true. A is false: backpropagation changes the weights (R is true).

A9.38Practice1 mark

Assertion (A): A GAN can create realistic images of faces that do not exist.

Reason (R): The generator improves by trying to fool the discriminator.

Answer

(a) Both A and R are true and R is the correct explanation of A. The generator keeps improving to fool the discriminator (R).

A9.39Practice1 mark

Assertion (A): Prompt engineering is useful for getting good output from an LLM.

Reason (R): A clear and specific prompt guides the model better.

Answer

(a) Both A and R are true and R is the correct explanation of A. Clear, specific prompts guide the model better (R).

A9.40Practice1 mark

Assertion (A): The output of generative AI needs no checking.

Reason (R): Generative AI can produce wrong or biased content.

Answer

(d) A is false but R is true. A is false: it can be wrong or biased (R is true), so it must be checked.

A9.41Practice1 mark

Assertion (A): The climax of a data story should carry the key insight.

Reason (R): The climax is the turning point of Freytag's Pyramid.

Answer

(a) Both A and R are true and R is the correct explanation of A. The climax is the turning point (R), the right place for the key insight (A).

A9.42Practice1 mark

Assertion (A): A line graph is suitable to show the change of temperature over a week.

Reason (R): A line graph shows a trend over time.

Answer

(a) Both A and R are true and R is the correct explanation of A. Line graphs show trends over time (R).

A9.43Practice1 mark

Assertion (A): Narrative is not needed if the charts are good.

Reason (R): A narrative explains what the data means and why it matters.

Answer

(d) A is false but R is true. A is false: the narrative explains what the data means (R is true).

AEEmployability skills: Assertion and Reason (5 per unit)1 mark · 25 questions
AE.1Practice1 mark

Assertion (A): Hearing and listening are the same.

Reason (R): Listening involves understanding and interpreting the message.

Answer

(d) A is false but R is true. Hearing is physical, listening is mental; A is false.

AE.2Practice1 mark

Assertion (A): Remembering is a stage of active listening.

Reason (R): The listener stores the message in memory to use later.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.3Practice1 mark

Assertion (A): Paraphrasing shows active listening.

Reason (R): It confirms that the listener has understood the message correctly.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.4Practice1 mark

Assertion (A): "A letter was written by Ravi" is in the active voice.

Reason (R): In the active voice the doer comes first.

Answer

(d) A is false but R is true. The sentence is passive; A is false; R is true.

AE.5Practice1 mark

Assertion (A): Names of months begin with capital letters.

Reason (R): The M in MINTS stands for months and days.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.6Practice1 mark

Assertion (A): Intrinsic motivation comes from within.

Reason (R): It is driven by interest and enjoyment of the task.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.7Practice1 mark

Assertion (A): In Maslow's hierarchy, self-actualisation is the most basic need.

Reason (R): Physiological needs such as food and water are at the base.

Answer

(d) A is false but R is true. Self-actualisation is the highest need; A is false.

AE.8Practice1 mark

Assertion (A): A result-oriented person focuses on achieving outcomes.

Reason (R): Such a person sets goals, plans and tracks progress.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.9Practice1 mark

Assertion (A): Openness is one of the Big Five personality factors.

Reason (R): People high in openness are curious and creative.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.10Practice1 mark

Assertion (A): People high in neuroticism are calm and emotionally stable.

Reason (R): Neuroticism is the tendency to feel anxious or upset easily.

Answer

(d) A is false but R is true. Low neuroticism means calm; A is false.

AE.11Practice1 mark

Assertion (A): Every formula in a spreadsheet begins with =.

Reason (R): The = sign tells the software that a calculation follows.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.12Practice1 mark

Assertion (A): Filtering deletes the rows that do not meet the condition.

Reason (R): Filtering only hides such rows temporarily.

Answer

(d) A is false but R is true. A is false; R is true.

AE.13Practice1 mark

Assertion (A): $A$1 is an absolute reference.

Reason (R): An absolute reference does not change when the formula is copied.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.14Practice1 mark

Assertion (A): A pie chart is best for showing a trend over time.

Reason (R): A line chart shows change over time.

Answer

(d) A is false but R is true. A is false; R is true.

AE.15Practice1 mark

Assertion (A): F5 starts a slide show from the first slide.

Reason (R): Shift + F5 starts from the current slide.

Answer

(b) Both A and R are true but R is not the correct explanation of A. Both are true, but R does not explain A.

AE.16Practice1 mark

Assertion (A): A dairy farm is an example of an agricultural entrepreneur.

Reason (R): Agricultural entrepreneurs work in farming and allied activities.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.17Practice1 mark

Assertion (A): A faulty business plan is a barrier to entrepreneurship.

Reason (R): A good plan studies customers, costs and profit before starting.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.18Practice1 mark

Assertion (A): Fear of failure is an environmental barrier.

Reason (R): Environmental barriers include lack of raw material, labour and roads.

Answer

(d) A is false but R is true. Fear of failure is a personal barrier; A is false.

AE.19Practice1 mark

Assertion (A): A successful entrepreneur sees problems as opportunities.

Reason (R): Solving people's problems creates demand for products and services.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.20Practice1 mark

Assertion (A): Break-even point is where total revenue equals total cost.

Reason (R): Beyond the break-even point the business makes profit.

Answer

(b) Both A and R are true but R is not the correct explanation of A. Both true; R does not define A.

AE.21Practice1 mark

Assertion (A): Green jobs help reduce greenhouse gases.

Reason (R): They promote renewable energy and efficient use of resources.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.22Practice1 mark

Assertion (A): Oxygen is a greenhouse gas.

Reason (R): Carbon dioxide and methane trap heat in the atmosphere.

Answer

(d) A is false but R is true. Oxygen is not a greenhouse gas; A is false.

AE.23Practice1 mark

Assertion (A): Solid waste management creates green jobs.

Reason (R): Segregation, composting and recycling need trained workers.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.24Practice1 mark

Assertion (A): NAPCC was launched to address climate change.

Reason (R): It has eight national missions including the National Solar Mission.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

AE.25Practice1 mark

Assertion (A): Eco-tourism is a field of green jobs.

Reason (R): Eco-tourism promotes nature-based travel that protects the environment.

Answer

(a) Both A and R are true and R is the correct explanation of A. Both statements are true, and R gives the reason why A is true.

Short answers · 2 marks each

B1Employability skills2 marks · 80 questions
B1.1SQP 2026-272 marks

Write any four barriers to active listening.

Answer

Thinking about your own reply while the other person speaks; distractions such as noise or the phone; lack of interest in the topic; judging the speaker before he or she finishes; day-dreaming; interrupting. (Any four.)

B1.2Practice2 marks

What does 'P' stand for in the acronym RESPECT used for active listening? Explain.

Answer

P stands for Pay attention: focus fully on what the speaker is saying and do not let the mind wander.

B1.3Practice2 marks

Expand the acronym RESPECT used for active listening.

Answer

Remove distractions; Eye contact; Show you are listening through gestures; Pay attention; Empathise with the speaker; Clarify doubts; Tune yourself to the timing of the speaker.

B1.4Practice2 marks

Name the five stages of active listening.

Answer

Receiving, Understanding, Remembering, Evaluating and Responding.

B1.5Practice2 marks

What is active listening? Why is it important?

Answer

Active listening means giving full attention to the speaker, understanding the message and responding to it. It avoids misunderstanding, builds trust and helps us to learn and work well with others.

B1.6Practice2 marks

Write two problems faced by a person who lacks communication skills.

Answer

Lack of communication skills leads to confusion, frustration, wasted effort and missed opportunities. The person cannot express ideas clearly or build good relations. (Any two.)

B1.7Practice2 marks

What is the MINTS rule of capitalisation?

Answer

Capital letters are used for: Months, the pronoun I, Names of people and places, Titles, and the Starting letter of a sentence.

B1.8Practice2 marks

Change into passive voice:

  1. Ravi wrote a letter.
  2. The chef cooks the food.
Answer

(i) A letter was written by Ravi. (ii) The food is cooked by the chef.

B1.9Practice2 marks

Name any four parts of speech with one example of each.

Answer

Noun: book. Pronoun: she. Verb: run. Adjective: tall. Adverb: quickly. Preposition: on. Conjunction: and. Interjection: wow. (Any four.)

B1.10Practice2 marks

Write two differences between hearing and listening.

Answer

(1) Hearing is only receiving sound through the ears; listening is understanding it with attention. (2) Hearing happens without effort; listening is an active skill that needs focus.

B1.11Practice2 marks

Write two tips to write a good paragraph.

Answer

(1) Keep one main idea in a paragraph, stated in the first (topic) sentence. (2) Add supporting sentences in a logical order and end with a concluding line; use correct grammar and punctuation.

B1.12SQP 2026-272 marks

Explain any two of the Big Five personality factors.

Answer

Openness: curious, creative, willing to try new things. Conscientiousness: organised, careful, dependable. Extraversion: outgoing, talkative, energetic. Agreeableness: kind, cooperative. Neuroticism: tendency to feel anxious or upset. (Any two.)

B1.13Practice2 marks

Write two differences between intrinsic and extrinsic motivation.

Answer

(1) Intrinsic motivation comes from within: we do the work because we enjoy it. Extrinsic motivation comes from outside: reward, salary, praise. (2) Intrinsic motivation lasts longer; extrinsic motivation stops when the reward stops.

B1.14Practice2 marks

Write any four techniques to become result oriented.

Answer

Set clear goals; prepare an action plan; use the right resources and tools; communicate with mentors and peers; make a calendar and work in the given time. (Any four.)

B1.15Practice2 marks

What is a personality disorder? Name the three clusters.

Answer

It is a way of thinking, feeling and behaving that is very different from what is expected, and causes problems in daily life. Cluster A: suspicious. Cluster B: emotional and impulsive. Cluster C: anxious.

B1.16Practice2 marks

Name any two personality disorders of Cluster A with one sign of each.

Answer

Paranoid: does not trust others, holds grudges. Schizoid: prefers to be alone, shows little emotion. Schizotypal: odd beliefs and behaviour. (Any two.)

B1.17Practice2 marks

Name any two personality disorders of Cluster B with one sign of each.

Answer

Antisocial: ignores the rights and feelings of others. Borderline: unstable moods and relations. Histrionic: seeks attention all the time. Narcissistic: thinks he or she is superior and wants praise. (Any two.)

B1.18Practice2 marks

Name any two personality disorders of Cluster C with one sign of each.

Answer

Avoidant: avoids people for fear of criticism. Dependent: depends on others for every decision. Obsessive-compulsive: wants perfect order and control. (Any two.)

B1.19Practice2 marks

Write two steps to overcome a personality disorder.

Answer

Talk to someone you trust or a counsellor; take up physical activity such as yoga, dance or sports; follow a hobby; choose positive thoughts. (Any two.)

B1.20Practice2 marks

What is self-awareness? How does it help?

Answer

Self-awareness is knowing your own strengths, weaknesses, values and feelings. It helps you to set the right goals, use your strengths and improve your weak areas.

B1.21Practice2 marks

What is a positive attitude? Write two ways to build it.

Answer

A positive attitude is seeing the good side of a situation and believing that problems can be solved. Ways: start the day with a healthy routine, stay with positive people, be thankful, learn from mistakes. (Any two.)

B1.22Practice2 marks

What is motivation? Why is self-motivation important for a student?

Answer

Motivation is the force that drives us to act to reach a goal. A self-motivated student studies regularly without being pushed, finishes work in time and does not give up after a failure.

B1.23SQP 2026-272 marks

A teacher has the marks of Classes IX to XII in one spreadsheet. She wants to see only the rows of Class XII. Which feature should she use, and how?

Answer

The Filter (AutoFilter) feature. Select the heading row, choose Data, AutoFilter, then open the drop-down arrow of the Class column and tick only XII. The other rows are hidden, not deleted.

B1.24Practice2 marks

Write two differences between sorting and filtering in a spreadsheet.

Answer

(1) Sorting arranges all the rows in ascending or descending order; filtering shows only the rows that meet a condition. (2) In sorting no row is hidden; in filtering the other rows are hidden.

B1.25Practice2 marks

Write any four advantages of presentation software.

Answer

Changes are easy to make; pictures, audio, video and animation make it interesting; it can be shown to a large audience on a projector; it can be shared and printed easily. (Any four.)

B1.26Practice2 marks

Name the spreadsheet function for each:

  1. Total
  2. Average
  3. Highest value
  4. Number of numeric cells.
Answer

(i) SUM (ii) AVERAGE (iii) MAX (iv) COUNT

B1.27Practice2 marks

What is a spreadsheet? Name two spreadsheet programs.

Answer

A spreadsheet is a program that stores data in rows and columns and does calculations, sorting and charting. Examples: LibreOffice Calc, Microsoft Excel, Google Sheets. (Any two.)

B1.28Practice2 marks

Why should a spreadsheet be protected with a password?

Answer

So that only authorised persons can open or change it. It keeps important data, such as marks or salaries, safe from accidental or wrongful changes.

B1.29Practice2 marks

What is a chart in a spreadsheet? Name two types.

Answer

A chart is a picture of the data that makes comparison easy. Types: bar or column chart, line chart, pie chart. (Any two.)

B1.30Practice2 marks

Write the formula to find:

  1. The total of the cells B2 to B10
  2. The highest value in the cells C2 to C10.
Answer

(i) =SUM(B2:B10) (ii) =MAX(C2:C10)

B1.31Practice2 marks

Write the steps to add a new slide and to start the slide show in presentation software.

Answer

New slide: Slide menu, New Slide (or Ctrl + M). Slide show: Slide Show menu, Start from First Slide (or press F5).

B1.32Practice2 marks

What is a cell reference? Give an example.

Answer

It is the address of a cell, made of the column letter and the row number. Example: B5 is the cell in column B and row 5.

B1.33Practice2 marks

Write two uses of a spreadsheet in a school.

Answer

Preparing result sheets with totals and percentages; keeping fee and attendance records; making charts of results. (Any two.)

B1.34SQP 2026-272 marks

What are organisational skills? Write any two of them.

Answer

They are the abilities to plan work and use time, money and people well. Skills: time management, planning and goal setting, setting priorities, delegating work, keeping records. (Any two.)

B1.35Practice2 marks

Who are business entrepreneurs?

Answer

They take up buying and selling (trading) of goods. They are not concerned with manufacturing. Example: a wholesaler or a shop owner.

B1.36Practice2 marks

Name any four types of entrepreneurs.

Answer

Service entrepreneurs, business (trading) entrepreneurs, industrial entrepreneurs, agricultural entrepreneurs, technical entrepreneurs, social entrepreneurs, women entrepreneurs. (Any four.)

B1.37Practice2 marks

Write any two barriers to entrepreneurship.

Answer

Environmental barriers: lack of raw material, labour, machinery or roads. No or faulty business plan. Personal barriers: self-doubt, fear of failure, lack of confidence. (Any two.)

B1.38Practice2 marks

Write any four entrepreneurial competencies.

Answer

Decisiveness, initiative, interpersonal skills, perseverance, organisational skills. (Any four, with a line on each.)

B1.39Practice2 marks

What is perseverance? Why does an entrepreneur need it?

Answer

Perseverance is continuing to work towards the goal in spite of difficulties. A new business faces losses and failures in the beginning; only a person who does not give up can succeed.

B1.40Practice2 marks

Write two differences between a service entrepreneur and an industrial entrepreneur.

Answer

(1) A service entrepreneur sells a service, such as teaching or repair; an industrial entrepreneur manufactures goods. (2) A service needs less machinery; manufacturing needs a factory, raw material and labour.

B1.41Practice2 marks

What is initiative? Give one example.

Answer

Initiative is starting a task on your own, before being told. Example: a shop owner starting home delivery when she sees customers cannot come to the shop.

B1.42Practice2 marks

What are interpersonal skills? Why are they needed in business?

Answer

They are the skills of dealing well with people: listening, speaking politely, teamwork and leadership. A business needs good relations with customers, workers and suppliers.

B1.43Practice2 marks

What is a social entrepreneur? Give one example.

Answer

A social entrepreneur starts an enterprise mainly to solve a problem of society, not only for profit. Example: an organisation that makes low-cost sanitary pads or gives solar lamps to villages.

B1.44Practice2 marks

Write two entrepreneurial attitudes.

Answer

Willingness to take risk, belief in oneself, openness to new ideas, and seeing a problem as an opportunity. (Any two.)

B1.45SQP 2026-272 marks

What is the main objective of the National Action Plan on Climate Change (NAPCC), 2008?

Answer

To promote development that also deals with climate change: to protect the poor and the environment, increase the use of renewable energy such as solar power, improve energy efficiency and save water and forests, through its eight national missions.

B1.46Practice2 marks

What are green jobs? Give two examples.

Answer

Green jobs are jobs that help to protect or restore the environment. Examples: solar panel technician, organic farmer, waste recycling worker, eco-tourism guide. (Any two.)

B1.47Practice2 marks

Explain the role of green jobs in eco-tourism.

Answer

Eco-tourism takes people to natural places without harming them. Guides, eco-lodge staff and forest workers educate tourists, protect wildlife and give income to the local people, so nature is conserved.

B1.48Practice2 marks

Write any four benefits of green jobs.

Answer

They limit greenhouse gas emissions; reduce waste and pollution; protect and restore ecosystems; save energy and raw material; help in adapting to climate change. (Any four.)

B1.49Practice2 marks

What is appropriate technology? Give one example.

Answer

It is small-scale, low-cost, environment-friendly technology that suits local needs. Example: a solar lamp, a biogas plant or a rainwater harvesting tank in a village.

B1.50Practice2 marks

Write two green jobs in the field of solid waste management.

Answer

Waste collector and sorter who separates dry and wet waste; recycling plant worker; compost maker. (Any two.)

B1.51Practice2 marks

What are greenhouse gases? Name any two.

Answer

Gases that trap the heat of the sun in the atmosphere and make the earth warmer. Examples: carbon dioxide, methane, nitrous oxide, water vapour. (Any two.)

B1.52Practice2 marks

Write two green jobs in transportation.

Answer

Driver or mechanic of electric and CNG vehicles; worker in the metro or other public transport; maker of bicycles and e-rickshaws. (Any two.)

B1.53Practice2 marks

How do green jobs help in water conservation? Give two examples.

Answer

Workers build rainwater harvesting systems and check dams; plumbers repair leaks and fit water-saving taps; operators run water treatment and recycling plants. (Any two.)

B1.54Practice2 marks

Write two green jobs in building and construction.

Answer

Architects and masons who make energy-saving green buildings; workers who install solar panels, insulation and rainwater systems. (Any two.)

B1.55Practice2 marks

Why are green jobs important for India? Write two points.

Answer

(1) They reduce pollution and the use of coal and petroleum. (2) They give employment to many people in solar energy, farming, waste management and tourism.

B1.56Practice2 marks

Write two differences between active voice and passive voice with an example.

Answer

(1) In active voice the subject does the action: "Meena sang a song." In passive voice the subject receives the action: "A song was sung by Meena." (2) Active voice is direct and short; passive voice is used when the doer is not important.

B1.57Practice2 marks

Write any four ways to become an active listener.

Answer

Remove distractions; keep eye contact; nod and show interest; do not interrupt; ask questions to clarify; repeat the main points in your own words. (Any four.)

B1.58Practice2 marks

Name the four types of sentences according to their purpose, with one example of each.

Answer

Declarative: I like tea. Interrogative: Do you like tea? Imperative: Bring the tea. Exclamatory: What a lovely tea!

B1.59Practice2 marks

Explain the stages 'Receiving' and 'Responding' of active listening.

Answer

Receiving: hearing the words and noticing the body language of the speaker with attention. Responding: giving feedback by words or gestures to show that the message is understood.

B1.60Practice2 marks

Why are communication skills important at the work place? Write two points.

Answer

(1) Clear communication avoids mistakes and saves time. (2) It builds good relations with team members and customers and helps in solving problems.

B1.61Practice2 marks

Explain Openness and Conscientiousness of the Big Five personality factors.

Answer

Openness: curious, creative, ready for new experiences. Conscientiousness: organised, disciplined, careful and dependable in work.

B1.62Practice2 marks

Explain Extraversion and Agreeableness of the Big Five personality factors.

Answer

Extraversion: outgoing, talkative, enjoys being with people. Agreeableness: kind, helpful, cooperative and trusting.

B1.63Practice2 marks

What is result orientation? Why is it needed?

Answer

It is focusing on the outcome and completing the work in the given time and quality. It helps a person to achieve goals, earn trust and grow in career.

B1.64Practice2 marks

Give one example each of intrinsic and extrinsic motivation from a student's life.

Answer

Intrinsic: solving puzzles because you enjoy them. Extrinsic: studying to win a scholarship or to get praise from parents.

B1.65Practice2 marks

Write two signs of narcissistic personality disorder and two of avoidant personality disorder.

Answer

Narcissistic: feels superior to others; wants constant praise. Avoidant: very shy; avoids people and new work for fear of criticism.

B1.66Practice2 marks

Write the steps to sort the data of a spreadsheet in ascending order of marks.

Answer

Select the data; open the Data menu and choose Sort; select the Marks column and Ascending; click OK.

B1.67Practice2 marks

Write two differences between a spreadsheet and presentation software.

Answer

(1) A spreadsheet stores and calculates data in rows and columns; presentation software shows information as slides. (2) A spreadsheet is used for analysis and charts; a presentation is used to explain ideas to an audience.

B1.68Practice2 marks

Write any four features of a spreadsheet.

Answer

Formulas and functions for calculation; sorting and filtering of data; charts; automatic recalculation when data changes; password protection. (Any four.)

B1.69Practice2 marks

What can be added to a slide of a presentation? Name any four.

Answer

Text, pictures, tables, charts, audio, video and animation. (Any four.)

B1.70Practice2 marks

Cell A1 has 20, A2 has 30 and A3 has 50. What will =SUM(A1:A3) and =AVERAGE(A1:A3) give?

Answer

=SUM(A1:A3) gives 100. =AVERAGE(A1:A3) gives 33.33 (100 divided by 3).

B1.71Practice2 marks

Write two differences between business entrepreneurs and industrial entrepreneurs.

Answer

(1) Business entrepreneurs buy and sell goods; industrial entrepreneurs manufacture goods. (2) Example: a wholesaler of clothes is a business entrepreneur; the owner of a garment factory is an industrial entrepreneur.

B1.72Practice2 marks

What is decisiveness? Why is it important for an entrepreneur?

Answer

Decisiveness is the ability to take clear and timely decisions. A business faces many choices every day; a delay in decisions causes loss of opportunity.

B1.73Practice2 marks

How can an entrepreneur overcome personal barriers? Write two ways.

Answer

(1) Build confidence through training, practice and small successes. (2) Take the help of mentors and family, and treat failure as learning.

B1.74Practice2 marks

Who are agricultural entrepreneurs? Give two examples.

Answer

They take up farming and related activities as a business. Examples: a dairy farm owner, a poultry farmer, an organic vegetable grower. (Any two.)

B1.75Practice2 marks

Why is a business plan important?

Answer

A business plan states the goal, the product, the customers, the cost and the expected income. It guides every decision and is needed to get a loan. A faulty or missing plan is a barrier to entrepreneurship.

B1.76Practice2 marks

Write two green jobs in agriculture.

Answer

Organic farmer who uses compost in place of chemicals; worker who makes vermicompost or bio-pesticides; technician of drip irrigation. (Any two.)

B1.77Practice2 marks

Write two green jobs in solar and wind energy.

Answer

Solar panel installer and maintenance technician; wind turbine technician; engineer who designs solar plants. (Any two.)

B1.78Practice2 marks

How do green jobs limit greenhouse gas emissions? Give one example.

Answer

They replace polluting activities with clean ones. Example: a solar technician helps homes to use sunlight in place of coal-based electricity, which reduces carbon dioxide.

B1.79Practice2 marks

Name any four missions of the National Action Plan on Climate Change.

Answer

National Solar Mission, National Water Mission, National Mission for a Green India, National Mission for Enhanced Energy Efficiency, National Mission for Sustainable Agriculture, National Mission on Sustainable Habitat. (Any four.)

B1.80Practice2 marks

What is eco-tourism? Write one benefit to local people.

Answer

Eco-tourism is travel to natural areas in a way that conserves the environment. Local people get jobs as guides, drivers and home-stay owners, so they protect the forest and wildlife.

B2AI units: explain and differentiate2 marks · 86 questions
B2.1SQP 2026-272 marks

What is model evaluation? Name its two phases.

Answer

Evaluation checks the quality of the model and whether it really answers the business problem. Phases: the diagnostic measures phase (is the model working as intended?) and the statistical significance phase (is the result reliable and not by chance?).

B2.2Practice2 marks

Define Data Science Methodology. How many steps does it have?

Answer

It is a step-by-step process that guides a data scientist from understanding the problem to deploying the solution and taking feedback. It has 10 steps.

B2.3Practice2 marks

Name the four types of analytic approach with the question each one answers.

Answer

Descriptive: what happened? Diagnostic: why did it happen? Predictive: what will happen? Prescriptive: what should be done?

B2.4Practice2 marks

Write two differences between the Data Requirements and Data Collection steps.

Answer

(1) Data Requirements decides what data is needed, in which format and from which sources; Data Collection actually gathers that data. (2) Requirements is planning; collection is doing, and it also checks for gaps in the data.

B2.5Practice2 marks

What is done in the Data Preparation step?

Answer

The data is cleaned: missing and wrong values and duplicates are handled. Data from different sources is combined, and new useful features are created (feature engineering). It takes the most time.

B2.6Practice2 marks

What is a train-test split?

Answer

The data is divided into two parts: a larger training set to build the model and a smaller testing set to check it on unseen data, for example 80% and 20%.

B2.7Practice2 marks

What is k-fold cross validation?

Answer

The data is divided into k equal folds. The model is trained k times; each time one fold is used for testing and the other k - 1 folds for training. The average of the k results is taken.

B2.8Practice2 marks

Can MSE be negative? Give a reason.

Answer

No. In MSE every error is squared, so each term is zero or positive. Their average cannot be negative.

B2.9Practice2 marks

Name any four evaluation metrics for classification.

Answer

Confusion matrix, accuracy, precision, recall and F1 score. (Any four.)

B2.10Practice2 marks

Write two differences between a descriptive model and a predictive model.

Answer

(1) A descriptive model shows the patterns in past data, such as groups of customers; a predictive model forecasts a future outcome. (2) Descriptive models use techniques such as clustering; predictive models use classification and regression.

B2.11Practice2 marks

Why is the Feedback step important?

Answer

After deployment, the users tell how the model performs in real use. This feedback is used to correct and refine the model, so the methodology works as a cycle.

B2.12SQP 2026-272 marks

Explain any two preprocessing techniques of computer vision with examples.

Answer

Noise reduction: removes unwanted grain or speckles, for example from a photo taken in low light. Normalisation: brings pixel values to a common range such as 0 to 1. Resizing/cropping: makes all the images the same size. (Any two.)

B2.13Practice2 marks

What is computer vision? Name two applications.

Answer

Computer vision is the field of AI that lets machines see, process and understand images and videos. Applications: face recognition, medical imaging, self-driving cars, surveillance. (Any two.)

B2.14Practice2 marks

Name the five stages of the computer vision process.

Answer

Image acquisition, preprocessing, feature extraction, detection/segmentation and high-level processing.

B2.15Practice2 marks

What is feature extraction? Name two techniques.

Answer

It finds the important visual patterns of an image that help to recognise objects. Techniques: edge detection, corner detection, texture analysis, colour-based feature extraction. (Any two.)

B2.16Practice2 marks

Write the difference between semantic segmentation and instance segmentation.

Answer

Semantic segmentation labels every pixel with a class; two cars get the same label. Instance segmentation also separates each object, so the two cars are marked as car 1 and car 2.

B2.17Practice2 marks

What is high-level processing? How is it different from the earlier stages?

Answer

It is the final stage, in which the detected objects are interpreted and a decision is taken, such as recognising a face or reading a number plate. The earlier stages only prepare the image and find features and objects.

B2.18Practice2 marks

Write two challenges of computer vision.

Answer

Reasoning and analytical issues; difficulty in getting good images (light, angle, hidden objects); privacy and security of people; duplicate and false content such as deepfakes. (Any two.)

B2.19Practice2 marks

Write two differences between image classification and object detection.

Answer

(1) Classification gives one label to the whole image; detection finds many objects and labels each. (2) Classification does not tell the position; detection marks each object with a box.

B2.20Practice2 marks

What is image acquisition? Name two devices used for it.

Answer

It is the first stage: capturing the image or video in digital form. Devices: digital camera, scanner, webcam, satellite or medical imaging sensor. (Any two.)

B2.21Practice2 marks

How does a computer see a colour image?

Answer

As a grid of pixels. Each pixel stores three numbers from 0 to 255, for red, green and blue. So a colour image is three layers (channels) of numbers.

B2.22Practice2 marks

Write two uses of computer vision in surveillance or transport.

Answer

Surveillance: detecting unusual activity and recognising faces in CCTV video. Transport: reading number plates at toll plazas; detecting lanes, vehicles and pedestrians for self-driving cars.

B2.23SQP 2026-272 marks

An OTT platform records what millions of users watch every second, as videos, clicks and reviews. Name and explain any two Vs of Big Data seen here.

Answer

Volume: a huge amount of data from millions of users. Velocity: data is produced every second and must be processed quickly. Variety: videos, clicks and text reviews are different types of data. (Any two.)

B2.24Practice2 marks

What is Big Data? Give two examples of its sources.

Answer

Big Data is data so large, fast and varied that traditional tools cannot store or process it. Sources: social media, online shopping, sensors, CCTV, banking transactions. (Any two.)

B2.25Practice2 marks

Name the three types of Big Data with one example of each.

Answer

Structured: an SQL table of marks. Semi-structured: an XML, JSON or CSV file. Unstructured: images, videos, audio, e-mails.

B2.26Practice2 marks

Name the six Vs of Big Data.

Answer

Volume, Velocity, Variety, Veracity, Value and Variability.

B2.27Practice2 marks

What is Big Data analytics? Why is it important?

Answer

It is the process of examining large and varied data to find hidden patterns, trends and customer preferences. It helps organisations to take better decisions, reduce cost and give better service.

B2.28Practice2 marks

Write two advantages and two disadvantages of Big Data.

Answer

Advantages: better decision making; better customer experience; new products. Disadvantages: risk to privacy and security; high cost and need of skilled people; poor quality data gives wrong results. (Any two each.)

B2.29Practice2 marks

What is mining of data streams?

Answer

A data stream is data that arrives continuously and at high speed, such as sensor readings or stock prices. Mining it means extracting useful patterns from the stream in real time, as the data cannot all be stored first.

B2.30Practice2 marks

Write two differences between structured and unstructured data.

Answer

(1) Structured data has a fixed format of rows and columns; unstructured data has no fixed format. (2) Structured data is easy to search with SQL; unstructured data such as images and videos needs special tools.

B2.31Practice2 marks

Explain Veracity and Value.

Answer

Veracity is the trustworthiness and quality of the data: wrong or biased data gives wrong results. Value is the usefulness of the data: data is worth collecting only if it gives benefit to the organisation.

B2.32Practice2 marks

Name any four tools used for Big Data analytics.

Answer

Tableau, Apache Hadoop, Cassandra, MongoDB, SAS. Apache Spark and Power BI are also used. (Any four.)

B2.33Practice2 marks

Write any two future trends in Big Data analytics.

Answer

Real-time analytics (insights as soon as the data arrives); more advanced models in predictive analytics; quantum computing (much faster processing of huge data). (Any two.)

B2.34SQP 2026-272 marks

Differentiate between the two propagation functions of a neural network.

Answer

Forward propagation: the input moves from the input layer through the hidden layers to the output layer to give a prediction. Backpropagation: the error is sent backwards from the output to adjust the weights and biases, so the loss becomes smaller.

B2.35Practice2 marks

What is a neural network? Name its three kinds of layers.

Answer

A neural network is a machine learning model made of connected units called neurons, inspired by the human brain. Layers: input layer, hidden layers and output layer.

B2.36Practice2 marks

What are weights and bias?

Answer

A weight is a number on a connection that shows how important that input is. The bias is an extra number added to the weighted sum, which shifts the output. Both are adjusted during training.

B2.37Practice2 marks

What is an activation function? Name any two.

Answer

It is a function applied to the weighted sum of a neuron to decide its output; it adds non-linearity. Examples: sigmoid, tanh, ReLU. (Any two.)

B2.38Practice2 marks

What is a loss function? Name one for regression and one for classification.

Answer

A loss function measures how far the predicted output is from the actual output. Regression: Mean Squared Error. Classification: binary cross-entropy (log loss).

B2.39Practice2 marks

Write two differences between CNN and RNN.

Answer

(1) A CNN is used for image data; an RNN is used for sequence data such as text and speech. (2) A CNN uses convolution filters to find features; an RNN has loops that remember earlier inputs.

B2.40Practice2 marks

What is a deep neural network?

Answer

A neural network with two or more hidden layers. More layers let it learn complex patterns, as in face recognition and speech recognition.

B2.41Practice2 marks

What is gradient descent?

Answer

It is the method by which a network reduces its loss: after each pass, the weights are changed by a small step in the direction that makes the loss smaller, until the loss is minimum.

B2.42Practice2 marks

Name any four types of neural networks.

Answer

Standard neural network (perceptron), feed-forward neural network, convolutional neural network, recurrent neural network, generative adversarial network. (Any four.)

B2.43Practice2 marks

What is a perceptron?

Answer

It is the simplest neural network, with a single layer of neurons. It adds the weighted inputs and the bias, applies an activation function and gives the output. It is also called the standard neural network.

B2.44Practice2 marks

Write two effects of neural networks on society.

Answer

Positive: better diagnosis of diseases, voice assistants, safer driving. Concern: loss of some jobs, bias in decisions, and misuse such as deepfakes. (One of each.)

B2.45SQP 2026-272 marks

What are deepfakes? Write their ethical and social effects with one example.

Answer

Deepfakes are AI-made fake videos, images or audio that look real. They can spread false news, damage a person's image and cheat people. Example: a fake video of a leader making a statement he never made.

B2.46Practice2 marks

What is generative AI? Give two examples of tools.

Answer

Generative AI is the part of AI that creates new content, such as text, images, audio and video, that resembles its training data. Tools: ChatGPT, Gemini, DALL-E, Canva, Stable Diffusion. (Any two.)

B2.47Practice2 marks

Write two differences between generative and discriminative models.

Answer

(1) A generative model learns how the data is distributed and creates new data; a discriminative model learns the boundary between classes and labels data. (2) Example: a GAN making faces is generative; a spam classifier is discriminative.

B2.48Practice2 marks

What is a GAN? Name its two parts.

Answer

A Generative Adversarial Network has two neural networks that compete. The generator makes fake samples; the discriminator tries to tell real from fake. Both improve until the fakes look real.

B2.49Practice2 marks

What is an LLM? Give two examples.

Answer

A Large Language Model is a deep learning model trained on a huge amount of text to understand and generate human language. Examples: GPT, Gemini, LLaMA. (Any two.)

B2.50Practice2 marks

Write any two limitations of LLMs.

Answer

They need very high processing power and data; they can give wrong answers confidently (hallucination); they can carry the bias of their training data; they do not truly understand. (Any two.)

B2.51Practice2 marks

Write any two ethical concerns of generative AI.

Answer

Deepfakes and false information; bias and discrimination in outputs; plagiarism and copyright of the training data; loss of privacy. (Any two.)

B2.52Practice2 marks

What is a Variational Autoencoder (VAE)?

Answer

A VAE is a generative model with an encoder that compresses the input into a small code and a decoder that rebuilds data from the code. By changing the code, new similar data can be generated.

B2.53Practice2 marks

Write two applications of generative AI.

Answer

Writing and summarising text; making images and designs from prompts; creating music and voice; generating video; writing computer code. (Any two.)

B2.54Practice2 marks

What is prompt engineering? Why is it needed?

Answer

It is the skill of writing a clear and specific instruction (prompt) for a generative AI tool. A better prompt gives a more accurate and useful output.

B2.55Practice2 marks

How can a student use generative AI responsibly? Write two points.

Answer

(1) Use it to learn and get ideas, not to copy; mention that AI was used. (2) Check the facts from reliable sources and do not create or share fake content.

B2.56SQP 2026-272 marks

What is data visualisation? Write its uses.

Answer

Data visualisation is showing data as charts, graphs and maps. It makes large data easy to understand, shows patterns, trends and outliers quickly, and helps in taking decisions.

B2.57Practice2 marks

What is data storytelling?

Answer

It is presenting the insights of data as a story, by combining data, narrative and visuals, so that the audience understands, remembers and acts on it.

B2.58Practice2 marks

Name the three key elements of data storytelling and the role of each.

Answer

Data: the facts and findings. Narrative: the story that explains the data. Visuals: charts that show the patterns.

B2.59Practice2 marks

Name the five stages of Freytag's Pyramid.

Answer

Introduction, rising action, climax, falling action and conclusion. (The introduction is also called the exposition and the conclusion the resolution.)

B2.60Practice2 marks

Write two differences between data visualisation and data storytelling.

Answer

(1) Visualisation shows the data as charts; storytelling adds a narrative that explains what the charts mean. (2) Visualisation tells what is happening; storytelling also tells why it matters and what should be done.

B2.61Practice2 marks

Which visualisation will you choose for:

  1. Text data
  2. Stock prices
  3. Data of different states
  4. A trend over time?
Answer

(i) Word cloud (ii) Candlestick chart (iii) Map (iv) Line graph

B2.62Practice2 marks

Why is a story more powerful than plain data? Write two points.

Answer

(1) Stories create interest and emotion, so people pay attention. (2) People remember a story much longer than a list of numbers, and are more likely to act.

B2.63Practice2 marks

Write the steps to create a data story.

Answer

Collect and organise the data; use visualisations to find insights; examine the relationships in the data; build a simple narrative with a problem and its solution, keeping the audience in mind.

B2.64Practice2 marks

Write two ethical points to follow in data storytelling.

Answer

(1) Show the data honestly: do not hide facts or change the scale of a graph to mislead. (2) Protect the privacy of the people in the data and name the source.

B2.65Practice2 marks

What happens when:

  1. Data is combined with narrative
  2. Data is combined with visuals?
Answer

(i) The narrative explains what is happening in the data. (ii) The visuals enlighten the audience by showing patterns and outliers that they would not see in the raw data.

B2.66Practice2 marks

What is a heat map? When is it used?

Answer

A heat map shows values with shades of colour in a grid. It is used to compare categories quickly, for example the sales of products in different months.

B2.67Practice2 marks

Explain image classification and classification with localisation.

Answer

Image classification gives one label to the whole image, such as 'cat'. Classification with localisation gives the label and also the position of that single object, by a box around it.

B2.68Practice2 marks

What is noise in an image? How is it handled?

Answer

Noise is the unwanted random variation in pixel values, seen as grain or speckles, caused by low light or a poor sensor. It is removed by noise reduction filters in the preprocessing stage.

B2.69Practice2 marks

Write two uses of computer vision in health care.

Answer

Detecting tumours, fractures and infections in X-ray, CT and MRI images; checking the retina for eye disease; helping surgeons with image-guided surgery. (Any two.)

B2.70Practice2 marks

Why is preprocessing needed in computer vision?

Answer

Raw images differ in size, brightness and quality, and may have noise. Preprocessing makes them clean and uniform, so that the features found later are correct.

B2.71Practice2 marks

Write two future trends of computer vision.

Answer

Personalised health-care diagnosis from medical images; immersive augmented reality (AR) experiences; systems that understand visual data with near-human precision. (Any two.) This progress needs teamwork and attention to ethics.

B2.72Practice2 marks

Explain Volume and Velocity with one example each.

Answer

Volume is the huge amount of data: a video site gets hundreds of hours of video every minute. Velocity is the speed of data: a stock exchange receives thousands of trades every second.

B2.73Practice2 marks

What is semi-structured data? Give two examples.

Answer

Data that has no fixed table but carries tags or keys that organise it. Examples: XML, JSON, CSV and HTML files. (Any two.)

B2.74Practice2 marks

Why must data be cleaned before analysis? Give an example.

Answer

Raw data has errors, missing values and duplicates. If the same customer is counted twice, the sales report will be wrong. Cleaning makes the result reliable.

B2.75Practice2 marks

How does Big Data help an online shopping company? Write two points.

Answer

(1) It studies what each customer views and buys, and recommends products. (2) It predicts demand, so that the right stock is kept and delivery is faster.

B2.76Practice2 marks

Write two differences between semi-structured and unstructured data.

Answer

(1) Semi-structured data has tags or keys (XML, JSON); unstructured data has no organisation at all (images, videos). (2) Semi-structured data is easier to search than unstructured data.

B2.77Practice2 marks

Name any four generative AI tools and the kind of content each creates.

Answer

ChatGPT and Gemini: text. DALL-E, Canva and Stable Diffusion: images. Google Lumiere and Animaker: video. Google MusicLM and Meta AI Voicebox: audio. (Any four.)

B2.78Practice2 marks

Write the roles of the generator and the discriminator in a GAN.

Answer

The generator creates fake samples from random noise and tries to make them look real. The discriminator examines real and fake samples and tries to tell them apart.

B2.79Practice2 marks

What is hallucination in an LLM? Give one example.

Answer

It is when the model gives a wrong or made-up answer in a confident way. Example: it gives the name of a book and author that do not exist.

B2.80Practice2 marks

Write two tips for writing a good prompt.

Answer

(1) Be clear and specific: state the task, the length and the audience. (2) Give context or an example, and ask for the format you want.

B2.81Practice2 marks

How can generative AI help teachers and students? Write two points.

Answer

It can explain a topic in simple words and make practice questions; it can summarise long text and give ideas for projects. The output must be checked.

B2.82Practice2 marks

What is a narrative in data storytelling?

Answer

It is the storyline that connects the facts: it explains what the data shows, why it happened and what should be done. It gives meaning to the numbers.

B2.83Practice2 marks

Explain the 'rising action' and 'climax' of Freytag's Pyramid in a data story.

Answer

Rising action: the facts that build the problem and create interest. Climax: the main finding or turning point, the most important insight of the story.

B2.84Practice2 marks

Why should the audience be kept in mind while making a data story?

Answer

Different audiences have different knowledge and needs. Managers want the decision; experts want details. The language, visuals and depth must suit them, or the message is lost.

B2.85Practice2 marks

Which chart will you use for:

  1. The share of each house in total points
  2. The marks of ten students in one test?
Answer

(i) Pie chart, because it shows the parts of a whole. (ii) Bar chart, because it compares separate values.

B2.86Practice2 marks

Name the elements of a story.

Answer

Characters, plot or setting, conflict (the problem), resolution (the solution) and insights.

B3Numericals for 2 marks2 marks · 48 questions
B3.1Practice2 marks

A model was tested on 100 cases. The results are: TP = 48, TN = 34, FP = 16, FN = 2. Calculate the accuracy and the error rate of the model.

Answer

Accuracy = (TP + TN) / Total = (48 + 34) / 100 = 82 / 100 = 0.82 (82%)

Error rate = 1 - Accuracy = (FP + FN) / Total = 18 / 100 = 0.18 (18%)

B3.2Practice2 marks

For a model, TP = 12, FP = 13 and FN = 12. Calculate its precision and recall.

Answer

Precision = TP / (TP + FP) = 12 / (12 + 13) = 12 / 25 = 0.48 (48%)

Recall = TP / (TP + FN) = 12 / (12 + 12) = 12 / 24 = 0.50 (50%)

B3.3Practice2 marks

The precision of a model is 0.90 and its recall is 0.60. Calculate the F1 score.

Answer

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.90 x 0.60 / (0.90 + 0.60) = 1.08 / 1.50 = 0.72

B3.4Practice2 marks

A model was tested on 200 cases. The results are: TP = 36, TN = 104, FP = 24, FN = 36. Calculate the accuracy and the error rate of the model.

Answer

Accuracy = (TP + TN) / Total = (36 + 104) / 200 = 140 / 200 = 0.70 (70%)

Error rate = 1 - Accuracy = (FP + FN) / Total = 60 / 200 = 0.30 (30%)

B3.5Practice2 marks

For a model, TP = 72, FP = 8 and FN = 28. Calculate its precision and recall.

Answer

Precision = TP / (TP + FP) = 72 / (72 + 8) = 72 / 80 = 0.90 (90%)

Recall = TP / (TP + FN) = 72 / (72 + 28) = 72 / 100 = 0.72 (72%)

B3.6Practice2 marks

The precision of a model is 0.50 and its recall is 0.60. Calculate the F1 score.

Answer

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.50 x 0.60 / (0.50 + 0.60) = 0.6 / 1.10 = 0.55

B3.7Practice2 marks

A model was tested on 50 cases. The results are: TP = 21, TN = 13, FP = 9, FN = 7. Calculate the accuracy and the error rate of the model.

Answer

Accuracy = (TP + TN) / Total = (21 + 13) / 50 = 34 / 50 = 0.68 (68%)

Error rate = 1 - Accuracy = (FP + FN) / Total = 16 / 50 = 0.32 (32%)

B3.8Practice2 marks

For a model, TP = 9, FP = 6 and FN = 3. Calculate its precision and recall.

Answer

Precision = TP / (TP + FP) = 9 / (9 + 6) = 9 / 15 = 0.60 (60%)

Recall = TP / (TP + FN) = 9 / (9 + 3) = 9 / 12 = 0.75 (75%)

B3.9Practice2 marks

The precision of a model is 0.90 and its recall is 0.60. Calculate the F1 score.

Answer

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.90 x 0.60 / (0.90 + 0.60) = 1.08 / 1.50 = 0.72

B3.10Practice2 marks

A model was tested on 100 cases. The results are: TP = 36, TN = 28, FP = 24, FN = 12. Calculate the accuracy and the error rate of the model.

Answer

Accuracy = (TP + TN) / Total = (36 + 28) / 100 = 64 / 100 = 0.64 (64%)

Error rate = 1 - Accuracy = (FP + FN) / Total = 36 / 100 = 0.36 (36%)

B3.11Practice2 marks

For a model, TP = 24, FP = 16 and FN = 8. Calculate its precision and recall.

Answer

Precision = TP / (TP + FP) = 24 / (24 + 16) = 24 / 40 = 0.60 (60%)

Recall = TP / (TP + FN) = 24 / (24 + 8) = 24 / 32 = 0.75 (75%)

B3.12Practice2 marks

The precision of a model is 0.60 and its recall is 0.40. Calculate the F1 score.

Answer

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.60 x 0.40 / (0.60 + 0.40) = 0.48 / 1.00 = 0.48

B3.13Practice2 marks

A model predicted the price of a shirt (in rupees) as 270. The actual value is 250. Calculate the error, the error rate and the accuracy of the prediction.

Answer

Error = |actual - predicted| = |250 - 270| = 20. Error rate = error / actual = 20 / 250 = 0.08 = 8%. Accuracy = 100% - 8% = 92%

B3.14Practice2 marks

A model predicted the marks of a class (total) as 380. The actual value is 400. Calculate the error, the error rate and the accuracy of the prediction.

Answer

Error = |actual - predicted| = |400 - 380| = 20. Error rate = error / actual = 20 / 400 = 0.05 = 5%. Accuracy = 100% - 5% = 95%

B3.15Practice2 marks

A model predicted the daily visitors of a park as 560. The actual value is 500. Calculate the error, the error rate and the accuracy of the prediction.

Answer

Error = |actual - predicted| = |500 - 560| = 60. Error rate = error / actual = 60 / 500 = 0.12 = 12%. Accuracy = 100% - 12% = 88%

B3.16Practice2 marks

A model predicted the units of electricity used as 720. The actual value is 800. Calculate the error, the error rate and the accuracy of the prediction.

Answer

Error = |actual - predicted| = |800 - 720| = 80. Error rate = error / actual = 80 / 800 = 0.10 = 10%. Accuracy = 100% - 10% = 90%

B3.17Practice2 marks

A model predicted the weight of a bag of rice (in grams) as 1040. The actual value is 1000. Calculate the error, the error rate and the accuracy of the prediction.

Answer

Error = |actual - predicted| = |1000 - 1040| = 40. Error rate = error / actual = 40 / 1000 = 0.04 = 4%. Accuracy = 100% - 4% = 96%

B3.18Practice2 marks

A model predicted the monthly sale of a shop (in rupees) as 1700. The actual value is 2000. Calculate the error, the error rate and the accuracy of the prediction.

Answer

Error = |actual - predicted| = |2000 - 1700| = 300. Error rate = error / actual = 300 / 2000 = 0.15 = 15%. Accuracy = 100% - 15% = 85%

B3.19Practice2 marks

An image has the resolution 640 x 480.

  1. How many pixels does it have?
  2. How many bytes are needed to store it as an 8-bit grayscale image and as an RGB image (without compression)?
Answer
(i)

Pixels = 640 x 480 = 307,200

(ii)

Grayscale: 1 byte per pixel = 307,200 bytes. RGB: 3 bytes per pixel = 307,200 x 3 = 921,600 bytes

B3.20Practice2 marks

An image has the resolution 1280 x 720.

  1. How many pixels does it have?
  2. How many bytes are needed to store it as an 8-bit grayscale image and as an RGB image (without compression)?
Answer
(i)

Pixels = 1280 x 720 = 921,600

(ii)

Grayscale: 1 byte per pixel = 921,600 bytes. RGB: 3 bytes per pixel = 921,600 x 3 = 2,764,800 bytes

B3.21Practice2 marks

An image has the resolution 100 x 100.

  1. How many pixels does it have?
  2. How many bytes are needed to store it as an 8-bit grayscale image and as an RGB image (without compression)?
Answer
(i)

Pixels = 100 x 100 = 10,000

(ii)

Grayscale: 1 byte per pixel = 10,000 bytes. RGB: 3 bytes per pixel = 10,000 x 3 = 30,000 bytes

B3.22Practice2 marks

An image has the resolution 1920 x 1080.

  1. How many pixels does it have?
  2. How many bytes are needed to store it as an 8-bit grayscale image and as an RGB image (without compression)?
Answer
(i)

Pixels = 1920 x 1080 = 2,073,600

(ii)

Grayscale: 1 byte per pixel = 2,073,600 bytes. RGB: 3 bytes per pixel = 2,073,600 x 3 = 6,220,800 bytes

B3.23Practice2 marks

An image has the resolution 800 x 600.

  1. How many pixels does it have?
  2. How many bytes are needed to store it as an 8-bit grayscale image and as an RGB image (without compression)?
Answer
(i)

Pixels = 800 x 600 = 480,000

(ii)

Grayscale: 1 byte per pixel = 480,000 bytes. RGB: 3 bytes per pixel = 480,000 x 3 = 1,440,000 bytes

B3.24Practice2 marks

An image has the resolution 256 x 256.

  1. How many pixels does it have?
  2. How many bytes are needed to store it as an 8-bit grayscale image and as an RGB image (without compression)?
Answer
(i)

Pixels = 256 x 256 = 65,536

(ii)

Grayscale: 1 byte per pixel = 65,536 bytes. RGB: 3 bytes per pixel = 65,536 x 3 = 196,608 bytes

B3.25Practice2 marks

The actual values are 82, 83, 47, 60 and the values predicted by a model are 82, 83, 47, 64. Calculate the MSE and the RMSE.

Answer

Errors: 0, 0, 0, -4. Squared errors: 0, 0, 0, 16. MSE = 16 / 4 = 4. RMSE = square root of 4 = 2

B3.26Practice2 marks

The actual values are 88, 102, 89, 116 and the values predicted by a model are 91, 99, 92, 119. Calculate the MSE and the RMSE.

Answer

Errors: -3, 3, -3, -3. Squared errors: 9, 9, 9, 9. MSE = 36 / 4 = 9. RMSE = square root of 9 = 3

B3.27Practice2 marks

The actual values are 70, 54, 121, 112 and the values predicted by a model are 69, 53, 126, 109. Calculate the MSE and the RMSE.

Answer

Errors: 1, 1, -5, 3. Squared errors: 1, 1, 25, 9. MSE = 36 / 4 = 9. RMSE = square root of 9 = 3

B3.28Practice2 marks

The actual values are 30, 10, 32, 43 and the values predicted by a model are 37, 15, 33, 38. Calculate the MSE and the RMSE.

Answer

Errors: -7, -5, -1, 5. Squared errors: 49, 25, 1, 25. MSE = 100 / 4 = 25. RMSE = square root of 25 = 5

B3.29Practice2 marks

The actual values are 55, 27, 24, 29 and the values predicted by a model are 51, 23, 28, 25. Calculate the MSE and the RMSE.

Answer

Errors: 4, 4, -4, 4. Squared errors: 16, 16, 16, 16. MSE = 64 / 4 = 16. RMSE = square root of 16 = 4

B3.30Practice2 marks

The actual values are 47, 52, 42 and the values predicted by a model are 40, 57, 43. Calculate the MSE and the RMSE.

Answer

Errors: 7, -5, -1. Squared errors: 49, 25, 1. MSE = 75 / 3 = 25. RMSE = square root of 25 = 5

B3.31Practice2 marks

The actual values are 95, 125, 118 and the values predicted by a model are 97, 127, 120. Calculate the MSE and the RMSE.

Answer

Errors: -2, -2, -2. Squared errors: 4, 4, 4. MSE = 12 / 3 = 4. RMSE = square root of 4 = 2

B3.32Practice2 marks

The actual values are 137, 137, 132, 68 and the values predicted by a model are 137, 133, 132, 68. Calculate the MSE and the RMSE.

Answer

Errors: 0, 4, 0, 0. Squared errors: 0, 16, 0, 0. MSE = 16 / 4 = 4. RMSE = square root of 4 = 2

B3.33Practice2 marks

The actual values are 12, 54, 15, 48 and the values predicted by a model are 15, 57, 18, 51. Calculate the MSE and the RMSE.

Answer

Errors: -3, -3, -3, -3. Squared errors: 9, 9, 9, 9. MSE = 36 / 4 = 9. RMSE = square root of 9 = 3

B3.34Practice2 marks

The actual values are 59, 50, 44, 21 and the values predicted by a model are 60, 53, 45, 16. Calculate the MSE and the RMSE.

Answer

Errors: -1, -3, -1, 5. Squared errors: 1, 9, 1, 25. MSE = 36 / 4 = 9. RMSE = square root of 9 = 3

B3.35Practice2 marks

A neuron has the inputs x1 = 1 and x2 = 2, the weights w1 = 3 and w2 = -2, and the bias -2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (1 x 3) + (2 x -2) + (-2) = -3

(ii)

ReLU(-3) = max(0, -3) = 0

B3.36Practice2 marks

A neuron has the inputs x1 = 5 and x2 = 2, the weights w1 = 3 and w2 = -1, and the bias 1.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (5 x 3) + (2 x -1) + (1) = 14

(ii)

ReLU(14) = max(0, 14) = 14

B3.37Practice2 marks

A neuron has the inputs x1 = 3 and x2 = 3, the weights w1 = -2 and w2 = -2, and the bias -6.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (3 x -2) + (3 x -2) + (-6) = -18

(ii)

ReLU(-18) = max(0, -18) = 0

B3.38Practice2 marks

A neuron has the inputs x1 = 1 and x2 = 2, the weights w1 = -1 and w2 = 1, and the bias -2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (1 x -1) + (2 x 1) + (-2) = -1

(ii)

ReLU(-1) = max(0, -1) = 0

B3.39Practice2 marks

A neuron has the inputs x1 = 5 and x2 = 1, the weights w1 = -2 and w2 = 1, and the bias -4.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (5 x -2) + (1 x 1) + (-4) = -13

(ii)

ReLU(-13) = max(0, -13) = 0

B3.40Practice2 marks

A neuron has the inputs x1 = 2 and x2 = 2, the weights w1 = -2 and w2 = 1, and the bias -6.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (2 x -2) + (2 x 1) + (-6) = -8

(ii)

ReLU(-8) = max(0, -8) = 0

B3.41Practice2 marks

A neuron has the inputs x1 = 1 and x2 = 5, the weights w1 = -1 and w2 = -2, and the bias -2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (1 x -1) + (5 x -2) + (-2) = -13

(ii)

ReLU(-13) = max(0, -13) = 0

B3.42Practice2 marks

A neuron has the inputs x1 = 1 and x2 = 2, the weights w1 = -1 and w2 = 1, and the bias -6.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (1 x -1) + (2 x 1) + (-6) = -5

(ii)

ReLU(-5) = max(0, -5) = 0

B3.43Practice2 marks

A neuron has the inputs x1 = 2 and x2 = 4, the weights w1 = 1 and w2 = 1, and the bias 2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (2 x 1) + (4 x 1) + (2) = 8

(ii)

ReLU(8) = max(0, 8) = 8

B3.44Practice2 marks

A neuron has the inputs x1 = 2 and x2 = 5, the weights w1 = 2 and w2 = 1, and the bias -2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (2 x 2) + (5 x 1) + (-2) = 7

(ii)

ReLU(7) = max(0, 7) = 7

B3.45Practice2 marks

A neuron has the inputs x1 = 3 and x2 = 1, the weights w1 = -1 and w2 = 3, and the bias -6.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (3 x -1) + (1 x 3) + (-6) = -6

(ii)

ReLU(-6) = max(0, -6) = 0

B3.46Practice2 marks

A neuron has the inputs x1 = 1 and x2 = 1, the weights w1 = -1 and w2 = 3, and the bias 2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (1 x -1) + (1 x 3) + (2) = 4

(ii)

ReLU(4) = max(0, 4) = 4

B3.47Practice2 marks

A neuron has the inputs x1 = 3 and x2 = 3, the weights w1 = -2 and w2 = 2, and the bias -2.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (3 x -2) + (3 x 2) + (-2) = -2

(ii)

ReLU(-2) = max(0, -2) = 0

B3.48Practice2 marks

A neuron has the inputs x1 = 1 and x2 = 3, the weights w1 = -1 and w2 = -1, and the bias 1.

  1. Calculate the weighted sum.
  2. What is the output if the activation function is ReLU?
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + bias = (1 x -1) + (3 x -1) + (1) = -3

(ii)

ReLU(-3) = max(0, -3) = 0

Long answers · 4 marks each

C1Long answers and case studies4 marks · 61 questions
C1.1SQP 2026-274 marks

Explain the working of Big Data analytics in four steps.

Answer

Step 1, Gather data: data is collected from many sources, such as cloud storage, mobile apps and sensors, in structured and unstructured forms. Step 2, Process data: the data is organised so that queries give correct results; it can be processed in batches or as a stream. Step 3, Clean data: errors, duplicates and irrelevant data are removed and the format is made uniform. Step 4, Analyse data: methods such as data mining, predictive analytics and deep learning turn the data into useful insights.

C1.2Practice4 marks

Explain the six Vs of Big Data with one line on each.

Answer

Volume: the huge amount of data. Velocity: the speed at which it is produced and processed. Variety: the different types: text, image, audio, video. Veracity: the trustworthiness and quality of the data. Value: the benefit the data gives. Variability: the changes in the flow and meaning of data with time.

C1.3Practice4 marks

Explain structured, semi-structured and unstructured data with two examples of each.

Answer

Structured: fixed rows and columns; SQL tables, spreadsheets. Semi-structured: has tags or keys but no fixed table; XML, JSON, CSV and HTML files. Unstructured: no fixed format; images, videos, audio, e-mails, social media posts. Most of the data in the world is unstructured.

C1.4Practice4 marks

Write two advantages and two disadvantages of Big Data. Explain each in one line.

Answer

Advantages: (1) Better decision making, from patterns found in the data. (2) Better customer experience, through personalised suggestions. Disadvantages: (1) Privacy and security: personal data may be leaked or misused. (2) Cost and skill: storage, tools and trained people are expensive; poor data quality gives wrong results.

C1.5Practice4 marks

A supermarket chain collects bills, CCTV video, app clicks and customer reviews.

  1. Classify each as structured, semi-structured or unstructured.
  2. Name two Vs seen here.
  3. Write two ways in which analytics will help the chain.
Answer

(i) Bills: structured. CCTV video and reviews: unstructured. App click logs (JSON): semi-structured. (ii) Volume and Variety (also Velocity). (iii) It can find which products sell together and stock them accordingly; it can give personalised offers and reduce waste.

C1.6Practice4 marks

What is mining of data streams? Why is it difficult? Give two examples of data streams.

Answer

A data stream is data that flows continuously and fast. Mining it means finding patterns in real time. It is difficult because the data is unlimited, cannot all be stored, and must be processed in one pass with limited memory. Examples: sensor readings of a factory, stock market prices, social media feeds.

C1.7Practice4 marks

Explain three future trends of Big Data analytics. Why do they matter?

Answer

Real-time analytics: data is analysed as soon as it arrives, so decisions are immediate, as in fraud alerts. Advanced models in predictive analytics: better machine learning models forecast demand, risk and behaviour more correctly. Quantum computing: very fast processing of huge and complex data. They matter because data keeps growing in volume and speed, and organisations need quicker and more correct decisions.

C1.8Practice4 marks

Differentiate between traditional data and Big Data in four points.

Answer

(1) Size: traditional data is in megabytes or gigabytes; Big Data is in terabytes and more. (2) Type: mostly structured; structured, semi-structured and unstructured. (3) Speed: produced slowly; produced every second. (4) Tools: a database such as MySQL; tools such as Hadoop and Spark.

C1.9Practice4 marks

How is Big Data analytics useful in:

  1. Health care
  2. Banking
  3. Education
  4. Transport? Write one use of each.
Answer

(i) Predicting outbreaks of disease and helping diagnosis from patient records. (ii) Detecting fraud from unusual transactions. (iii) Finding weak areas of students and personalising learning. (iv) Planning routes and reducing traffic jams from GPS data.

C1.10Practice4 marks

What is Big Data analytics? Name four tools and write one line on any two.

Answer

It is the process of examining very large and varied data to find patterns and insights. Tools: Tableau, Apache Hadoop, Cassandra, MongoDB, SAS. Hadoop stores and processes huge data on many computers together. Tableau makes interactive charts and dashboards from data.

C1.11SQP 2026-274 marks
  1. Expand LLM.
  2. Give two examples of LLMs.
  3. Write two limitations of LLMs.
Answer

(i) Large Language Model. (ii) GPT (used in ChatGPT), Gemini, LLaMA. (Any two.) (iii) They need very high processing power and huge data. They can give wrong or made-up answers confidently (hallucination) and can carry bias from the training data.

C1.12Practice4 marks

Differentiate between generative and discriminative models in four points.

Answer

(1) Aim: a generative model creates new data; a discriminative model classifies data. (2) Learning: learns how the data is distributed; learns the boundary between classes. (3) Output: a new image, text or sound; a label. (4) Examples: GAN, VAE; logistic regression, a spam classifier.

C1.13Practice4 marks

Explain the working of a GAN.

Answer

A GAN has two networks. The generator takes random noise and produces fake samples. The discriminator gets real samples and fake samples and tries to tell them apart. Its result is sent back to both: the generator learns to make better fakes, the discriminator learns to catch them. Training continues until the fakes look real.

C1.14Practice4 marks

Explain any four applications of generative AI with one tool for each.

Answer

Text: writing, summarising, answering; ChatGPT, Gemini. Image: pictures from prompts; Canva, DALL-E, Stable Diffusion. Video: clips from text; Google Lumiere, Animaker. Audio: music and voice; Google MusicLM, Meta AI Voicebox. It is also used to write computer code.

C1.15Practice4 marks

Explain the ethical and social implications of generative AI in four points.

Answer

Deepfakes: fake videos spread false information. Bias and discrimination: outputs repeat the bias of the training data. Plagiarism and copyright: content is produced from others' work and may be passed off as one's own. Transparency: users may not know that the content is made by AI. Jobs of some creators may also be affected.

C1.16Practice4 marks

What are LLMs? Write two applications and two risks.

Answer

Large Language Models are deep learning models trained on huge text to understand and generate language. Applications: chatbots and virtual assistants; translation, summarising and writing code. Risks: wrong information given confidently; misuse for spam, cheating and fake news; bias.

C1.17Practice4 marks

Explain the working of the two generative models, GAN and VAE. Name the parts of each.

Answer

GAN (Generative Adversarial Network): it has a generator, which creates new samples, and a discriminator, which judges whether a sample is real or fake. The two compete, so the generated data becomes more and more realistic. VAE (Variational Autoencoder): it has an encoder, which compresses the data into a small code (latent space), and a decoder, which rebuilds data from that code. By changing the code, new similar data is generated.

C1.18Practice4 marks

A student uses an AI tool to write a full project report and submits it as her own. Discuss the issue and suggest three good practices.

Answer

It is plagiarism: the work is not hers, and the content may have errors or copied material. Good practices: (1) use AI only for ideas and write in her own words; (2) verify every fact from reliable sources; (3) state clearly where AI was used and cite sources.

C1.19Practice4 marks

What are deepfakes? How are they made? Write two harms and two ways to stay safe.

Answer

Deepfakes are fake videos, images or audio of real people made with generative AI, usually GANs. Harms: false news and damage to a person's image; fraud by copying a voice or face. Safety: check the source before believing or sharing; look for unnatural movement or voice; report fake content.

C1.20Practice4 marks

Compare any two generative AI tools for images with any two for text.

Answer

Images: DALL-E and Stable Diffusion create pictures from a text prompt; Canva also has a text-to-image tool. Text: ChatGPT and Gemini answer questions, write and summarise text and code. Image tools give pictures as output; text tools give language as output; both need a clear prompt.

C1.21SQP 2026-274 marks

What is data storytelling? Explain its key elements.

Answer

Data storytelling is communicating the insights of data through a story. Its three elements: Data: the facts, found by analysis. Narrative: the storyline that explains what the data means and why it matters. Visuals: charts and graphs that show the patterns. Data with narrative explains; data with visuals enlightens; narrative with visuals engages; all three together can drive change.

C1.22Practice4 marks

Explain Freytag's Pyramid for a data story.

Answer

Introduction: give the setting, the characters and the question. Rising action: show the data that builds the problem. Climax: the main insight, the turning point. Falling action: what follows from the insight, with supporting facts. Conclusion: the problem is resolved and the action is suggested.

C1.23Practice4 marks

Write the steps to create a data story.

Answer

(1) Collect the data and organise it. (2) Use proper visualisation tools to visualise the data. (3) Observe the relationships in the data. (4) Create a simple narrative, hidden in the data, to communicate to the audience.

C1.24Practice4 marks

Which visualisation suits each type of data? Give five pairs.

Answer

Text data: word cloud. Numeric data over time: line graph. Stock prices: candlestick chart. Geographic data: map. Comparison of categories by colour: heat map. Mixed data for groups: facet grid.

C1.25Practice4 marks

Why is data storytelling powerful? Explain with the three combinations of its elements.

Answer

Data + narrative explains what is happening and why it is important. Data + visuals enlightens: the audience sees patterns and outliers. Narrative + visuals engages the audience. When all three come together, the story can influence people and drive change.

C1.26Practice4 marks

A school finds that attendance falls every Monday. Plan a data story on this using Freytag's Pyramid.

Answer

Introduction: the school tracks daily attendance. Rising action: a line graph shows a dip on every Monday. Climax: the dip is largest for students who travel far. Falling action: Monday tests and lost learning are linked to the dip. Conclusion: suggest a Monday activity period and a bus timing change.

C1.27Practice4 marks

Write four ethical practices to follow in data storytelling.

Answer

(1) Be accurate: do not change or hide data. (2) Do not mislead with cut scales or selected data only. (3) Protect privacy: remove names and personal details. (4) Be transparent: tell the source and the limits of the data.

C1.28Practice4 marks

Differentiate between a story, data visualisation and data storytelling.

Answer

A story is a narrative with characters, a conflict and a resolution; it needs no data. Data visualisation shows data as charts; it has no narrative. Data storytelling combines data, visuals and a narrative so that the audience understands the insight and acts on it.

C1.29Practice4 marks

What are the elements of a story? How are they used in a data story?

Answer

Characters, plot or setting, conflict, resolution and insights. In a data story: the characters are the people affected (customers, students); the setting is the time and place of the data; the conflict is the problem shown by the data; the resolution is the solution suggested; the insights are what the audience learns.

C1.30Practice4 marks

Explain with an example how a good visual improves a data story.

Answer

A table of monthly sales of 12 months is hard to read. A line graph of the same data shows at once that sales fall in the rainy months. A highlight on that dip, with a line of text, directs the audience to the key insight and makes it easy to remember.

C1.31SQP 2026-274 marks

What is data modelling? Explain descriptive and predictive models with the techniques used.

Answer

Modelling is the step in which a model is built from the prepared data to answer the question. Descriptive models show what has happened and find patterns; techniques: clustering, summary statistics, association. Predictive models forecast future outcomes; techniques: classification (for a category) and regression (for a number). The model is trained on a training set and tested on a test set.

C1.32Practice4 marks

Name the ten steps of the Data Science Methodology in order.

Answer

Business Understanding, Analytic Approach, Data Requirements, Data Collection, Data Understanding, Data Preparation, Modelling, Evaluation, Deployment, Feedback.

C1.33Practice4 marks

Explain the four types of analytic approach with one example of each.

Answer

Descriptive: what happened? Last year's sales report. Diagnostic: why did it happen? Finding why sales fell in June. Predictive: what will happen? Forecasting next month's sales. Prescriptive: what should be done? Suggesting a discount to increase sales.

C1.34Practice4 marks

Explain train-test split and k-fold cross validation. Which is more reliable, and why?

Answer

Train-test split: the data is divided once into a training set and a testing set. k-fold cross validation: the data is divided into k folds; the model is trained k times, each time testing on a different fold, and the results are averaged. Cross validation is more reliable because every record is used for testing once; but it takes more time.

C1.35Practice4 marks

Explain the steps Business Understanding, Analytic Approach, Data Requirements and Data Collection in one line each.

Answer

Business Understanding: define the problem and the goal clearly. Analytic Approach: decide how data can answer it: descriptive, diagnostic, predictive or prescriptive. Data Requirements: decide what data, format and sources are needed. Data Collection: gather the data and check for gaps.

C1.36SQP 2026-274 marks

What is a neural network? Explain its layers.

Answer

A neural network is a machine learning model made of layers of connected neurons, inspired by the brain. Input layer: receives the features of the data, one neuron for each feature. Hidden layers: each neuron multiplies inputs by weights, adds a bias and applies an activation function; these layers find the patterns. Output layer: gives the final prediction. A network with two or more hidden layers is a deep neural network.

C1.37Practice4 marks

Explain the working of a neural network using the terms forward propagation, loss function and backpropagation.

Answer

In forward propagation the input passes through the layers: each neuron finds the weighted sum plus bias and applies the activation function, and the output layer gives a prediction. The loss function measures the error between the prediction and the actual value. In backpropagation this error is sent backwards and the weights and biases are adjusted by gradient descent. The cycle repeats for many epochs.

C1.38Practice4 marks

Explain any four types of neural networks with one use of each.

Answer

Perceptron (standard NN): single layer; simple yes/no classification. Feed-forward NN: data moves one way through hidden layers; predicting marks or prices. CNN: uses convolution filters; image recognition. RNN: has memory of earlier inputs; text and speech. (GAN: generator and discriminator; creating images.)

C1.39Practice4 marks

Explain the components of a neural network: neurons, weights, bias and activation function.

Answer

Neurons: the units that receive inputs, process them and pass an output. Weights: numbers on the connections that show the importance of each input. Bias: an extra value added to the weighted sum to shift the output. Activation function: decides the output of the neuron and adds non-linearity; examples are sigmoid, tanh and ReLU.

C1.40Practice4 marks

Describe the structure of an artificial neural network by its three layers, and explain the role of weights.

Answer

The input layer takes the data. The hidden layers do the computation. The output layer gives the result. Every connection between two neurons has a weight. The weight decides how much one neuron's output affects the next neuron. Training means adjusting these weights so that the output becomes correct.

C1.41Practice4 marks

Explain Volume, Velocity, Variety and Veracity with the example of a social media platform.

Answer

Volume: billions of posts, photos and videos are stored. Velocity: thousands of new posts arrive every second and must be shown at once. Variety: text, images, videos, likes and locations are different types of data. Veracity: fake accounts and false news reduce the trustworthiness of the data.

C1.42Practice4 marks

A city wants to use Big Data from traffic cameras, GPS of buses and mobile apps to reduce traffic jams. Explain how the four steps of Big Data analytics will be applied.

Answer

Gather: collect video, GPS and app data from all the sources. Process: bring the data to one platform and organise it, mostly as a live stream. Clean: remove faulty readings and duplicates. Analyse: find the busy routes and hours, predict jams and change signal timings and bus routes.

C1.43Practice4 marks

What is Big Data? Write three of its sources and three areas where it is used.

Answer

Big Data is data too large, fast and varied for traditional tools. Sources: social media, online transactions, sensors and CCTV. Uses: health care (predicting disease), banking (fraud detection), retail (recommendations), transport (route planning). (Any three each.)

C1.44Practice4 marks

Explain the terms:

  1. Data stream
  2. Real-time analytics
  3. Data analytics
  4. Unstructured data.
Answer

(i) Data that flows continuously at high speed, such as sensor readings. (ii) Analysing data as soon as it arrives, so that the decision is immediate. (iii) Examining data to find patterns and insights for decisions. (iv) Data with no fixed format, such as images and videos.

C1.45Practice4 marks

Write four challenges (disadvantages) of Big Data and one way to handle each.

Answer

(1) Privacy: take consent and hide personal details. (2) Security: encrypt and control access. (3) Data quality: clean and verify the data. (4) Cost and skill: use cloud services and train staff.

C1.46Practice4 marks

Compare structured, semi-structured and unstructured data on format, example, storage and ease of analysis.

Answer

Structured: fixed rows and columns; marks table; relational database; easy. Semi-structured: tags or keys; JSON, XML; NoSQL stores; moderate. Unstructured: no format; videos, images; data lakes and file systems; difficult, needs AI tools.

C1.47Practice4 marks

Explain sigmoid, tanh and ReLU activation functions with the range of each.

Answer

Sigmoid: squeezes any input to a value between 0 and 1; used for probability in the output layer. tanh: gives values between -1 and 1; centred at zero. ReLU: gives 0 for a negative input and the same value for a positive input; simple and fast, most used in hidden layers.

C1.48Practice4 marks

What is a loss function? Explain how gradient descent uses it to train a network.

Answer

A loss function measures the error between the predicted and the actual output (MSE for regression, log loss for classification). Gradient descent finds in which direction each weight should change to reduce the loss, and changes it by a small step set by the learning rate. This is repeated for many epochs until the loss is minimum.

C1.49Practice4 marks

Write two positive impacts and two concerns of neural networks for society, with examples.

Answer

Positive: (1) early and accurate diagnosis from medical images; (2) voice assistants and translation that help people. Concerns: (1) bias in decisions such as hiring or loans; (2) misuse for deepfakes and loss of some jobs. Their decisions are also hard to explain.

C1.50Practice4 marks

Explain the working of generative AI in simple steps, with an example.

Answer

(1) A model is trained on a very large data set, such as millions of images. (2) It learns the patterns and structure of that data. (3) Given a prompt, it produces new content that follows those patterns. (4) The output is refined with feedback. Example: a prompt 'a red kite in a blue sky' gives a new image.

C1.51Practice4 marks

What is a Large Language Model? Explain how it is used in a chatbot and write two precautions for users.

Answer

An LLM is a deep learning model trained on huge text to understand and generate language. In a chatbot, it reads the user's prompt and predicts a suitable reply, word by word. Precautions: verify the facts, because it can hallucinate; do not share personal or secret data.

C1.52Practice4 marks

Explain four benefits of generative AI in education, business, design and health care.

Answer

Education: explanations and practice questions for each learner. Business: drafts of e-mails, reports and customer replies. Design: quick images, logos and layouts from prompts. Health care: help in studying new medicines and making synthetic medical images for training.

C1.53Practice4 marks

Differentiate between a GAN and a VAE in four points.

Answer

(1) Parts: generator and discriminator / encoder and decoder. (2) Working: two networks compete / data is compressed to a code and rebuilt. (3) Output: very sharp, realistic images / smoother, slightly blurred images. (4) Training: harder to train / more stable.

C1.54Practice4 marks

A fake audio clip of a school principal announcing a holiday goes viral. Discuss the issue, its effects and what students should do.

Answer

It is a deepfake: an AI-made fake audio. Effects: confusion, loss of trust, harm to the person's image. Students should check with the official school notice or teacher, not forward the clip, and report it. Making such clips is an offence.

C1.55Practice4 marks

Explain the legal and social issues of generative AI: copyright, privacy, jobs and misinformation.

Answer

Copyright: models are trained on others' work; ownership of the output is unclear. Privacy: personal data may appear in training data or outputs. Jobs: some writing and design work may reduce, while new jobs come up. Misinformation: fake news and deepfakes spread fast.

C1.56Practice4 marks

A shopkeeper has two years of monthly sales data. Explain how she can turn it into a data story.

Answer

Collect and organise the data month-wise. Draw a line graph to find the pattern, for example a fall every summer. Find the reason by comparing with holidays and stock. Build the narrative: background, the falling sales (conflict), the main insight (climax), and the solution, such as summer offers (resolution). Present it in simple words to the staff.

C1.57Practice4 marks

Explain with examples how choosing the wrong chart can mislead the audience.

Answer

A pie chart with too many slices hides small differences. A bar chart whose axis does not start at zero makes a small change look big. A 3D chart distorts sizes. The right chart, with a full scale and clear labels, shows the truth.

C1.58Practice4 marks

Why do we need data storytelling? Write four points.

Answer

(1) Large data is hard to understand; a story makes it simple. (2) Stories are remembered longer than numbers. (3) A story connects with emotion and persuades people to act. (4) It brings out the key insight for decision makers.

C1.59Practice4 marks

Compare a word cloud, a heat map, a line graph and a candlestick chart: what each shows and when it is used.

Answer

Word cloud: frequent words appear bigger; text data such as reviews. Heat map: values as shades of colour; comparing categories. Line graph: points joined by a line; trend over time. Candlestick chart: opening, closing, high and low prices; stock data.

C1.60Practice4 marks

Write a short data story plan on 'screen time of Class XII students' using data, narrative and visuals.

Answer

Data: a survey of daily screen hours and test marks. Visuals: a bar chart of screen hours and a scatter plot of screen time against marks. Narrative: students use screens for five hours on average; marks fall as screen time rises; the story ends with a suggestion to limit screen time before exams.

C1.61Practice4 marks

Explain the falling action and the conclusion of a data story with an example.

Answer

Falling action follows the main insight: it gives supporting facts and what the insight means. The conclusion is the last part: the problem is resolved and the action is suggested. Example: after showing that most road accidents occur at night (climax), the story shows the low lighting on those roads (falling action) and recommends street lights (conclusion).

C2Confusion matrix, MSE and RMSE numericals4 marks · 30 questions
C2.1Practice4 marks

The confusion matrix of a disease-screening AI, tested on 50 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: has the diseaseReality: is healthy
Predicted: has the disease21TP14FP
Predicted: is healthy7FN8TN
Answer
(i)

Accuracy = (TP + TN) / Total = (21 + 8) / 50 = 29 / 50 = 0.58 (58%)

(ii)

Precision = TP / (TP + FP) = 21 / (21 + 14) = 21 / 35 = 0.60 (60%)

(iii)

Recall = TP / (TP + FN) = 21 / (21 + 7) = 21 / 28 = 0.75 (75%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.60 x 0.75 / (0.60 + 0.75) = 0.9 / 1.35 = 0.67

C2.2Practice4 marks

A regression model predicts the marks of students. The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual75746149
Predicted77766351
Answer
(i)
CaseActualPredictedError
17577-2
27476-2
36163-2
44951-2
(ii)

Squared errors: (-2)2 = 4, (-2)2 = 4, (-2)2 = 4, (-2)2 = 4

(iii)

MSE = sum of squared errors / number of cases = (4 + 4 + 4 + 4) / 4 = 16 / 4 = 4

(iv)

RMSE = square root of MSE = square root of 4 = 2

C2.3Practice4 marks

A spam filter was tested on 50 cases. It predicted 'spam' for 30 cases; out of these, 18 were really 'spam'. It predicted 'genuine mail' for the other 20 cases; out of these, 13 were really 'genuine mail'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 18, FP = 30 - 18 = 12, TN = 13, FN = 20 - 13 = 7.

Confusion matrix

Reality: spamReality: genuine mail
Predicted: spam18TP12FP
Predicted: genuine mail7FN13TN
(ii)

Accuracy = (TP + TN) / Total = (18 + 13) / 50 = 31 / 50 = 0.62 (62%)

Precision = TP / (TP + FP) = 18 / (18 + 12) = 18 / 30 = 0.60 (60%)

Recall = TP / (TP + FN) = 18 / (18 + 7) = 18 / 25 = 0.72 (72%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.60 x 0.72 / (0.60 + 0.72) = 0.864 / 1.32 = 0.65

(iii)

Precision, because a genuine mail sent to the spam folder (False Positive) may be an important message.

C2.4Practice4 marks

A regression model predicts the price of houses (in lakh rupees). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual35614245
Predicted35614249
Answer
(i)
CaseActualPredictedError
135350
261610
342420
44549-4
(ii)

Squared errors: (0)2 = 0, (0)2 = 0, (0)2 = 0, (-4)2 = 16

(iii)

MSE = sum of squared errors / number of cases = (0 + 0 + 0 + 16) / 4 = 16 / 4 = 4

(iv)

RMSE = square root of MSE = square root of 4 = 2

C2.5Practice4 marks

The confusion matrix of a forest-fire alert system, tested on 1000 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: fireReality: no fire
Predicted: fire240TP80FP
Predicted: no fire260FN420TN
Answer
(i)

Accuracy = (TP + TN) / Total = (240 + 420) / 1000 = 660 / 1000 = 0.66 (66%)

(ii)

Precision = TP / (TP + FP) = 240 / (240 + 80) = 240 / 320 = 0.75 (75%)

(iii)

Recall = TP / (TP + FN) = 240 / (240 + 260) = 240 / 500 = 0.48 (48%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.75 x 0.48 / (0.75 + 0.48) = 0.72 / 1.23 = 0.59

C2.6Practice4 marks

A regression model predicts the daily temperature (in Celsius). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual36282220
Predicted30282220
Answer
(i)
CaseActualPredictedError
136306
228280
322220
420200
(ii)

Squared errors: (6)2 = 36, (0)2 = 0, (0)2 = 0, (0)2 = 0

(iii)

MSE = sum of squared errors / number of cases = (36 + 0 + 0 + 0) / 4 = 36 / 4 = 9

(iv)

RMSE = square root of MSE = square root of 9 = 3

C2.7Practice4 marks

A bank's fraud detector was tested on 1000 cases. It predicted 'fraud' for 520 cases; out of these, 260 were really 'fraud'. It predicted 'genuine transaction' for the other 480 cases; out of these, 240 were really 'genuine transaction'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 260, FP = 520 - 260 = 260, TN = 240, FN = 480 - 240 = 240.

Confusion matrix

Reality: fraudReality: genuine transaction
Predicted: fraud260TP260FP
Predicted: genuine transaction240FN240TN
(ii)

Accuracy = (TP + TN) / Total = (260 + 240) / 1000 = 500 / 1000 = 0.50 (50%)

Precision = TP / (TP + FP) = 260 / (260 + 260) = 260 / 520 = 0.50 (50%)

Recall = TP / (TP + FN) = 260 / (260 + 240) = 260 / 500 = 0.52 (52%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.50 x 0.52 / (0.50 + 0.52) = 0.52 / 1.02 = 0.51

(iii)

Recall, because a fraud that is missed (False Negative) causes a loss of money.

C2.8Practice4 marks

A regression model predicts the sales of a shop (in thousand rupees). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual13194121131
Predicted12891118128
Answer
(i)
CaseActualPredictedError
11311283
294913
31211183
41311283
(ii)

Squared errors: (3)2 = 9, (3)2 = 9, (3)2 = 9, (3)2 = 9

(iii)

MSE = sum of squared errors / number of cases = (9 + 9 + 9 + 9) / 4 = 36 / 4 = 9

(iv)

RMSE = square root of MSE = square root of 9 = 3

C2.9Practice4 marks

The confusion matrix of a plagiarism checker, tested on 200 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: copied workReality: original work
Predicted: copied work32TP48FP
Predicted: original work8FN112TN
Answer
(i)

Accuracy = (TP + TN) / Total = (32 + 112) / 200 = 144 / 200 = 0.72 (72%)

(ii)

Precision = TP / (TP + FP) = 32 / (32 + 48) = 32 / 80 = 0.40 (40%)

(iii)

Recall = TP / (TP + FN) = 32 / (32 + 8) = 32 / 40 = 0.80 (80%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.40 x 0.80 / (0.40 + 0.80) = 0.64 / 1.20 = 0.53

C2.10Practice4 marks

A regression model predicts the runs scored by a batter. The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual52702239
Predicted52642231
Answer
(i)
CaseActualPredictedError
152520
270646
322220
439318
(ii)

Squared errors: (0)2 = 0, (6)2 = 36, (0)2 = 0, (8)2 = 64

(iii)

MSE = sum of squared errors / number of cases = (0 + 36 + 0 + 64) / 4 = 100 / 4 = 25

(iv)

RMSE = square root of MSE = square root of 25 = 5

C2.11Practice4 marks

A face-unlock system (positive = owner) was tested on 500 cases. It predicted 'owner' for 250 cases; out of these, 150 were really 'owner'. It predicted 'stranger' for the other 250 cases; out of these, 200 were really 'stranger'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 150, FP = 250 - 150 = 100, TN = 200, FN = 250 - 200 = 50.

Confusion matrix

Reality: ownerReality: stranger
Predicted: owner150TP100FP
Predicted: stranger50FN200TN
(ii)

Accuracy = (TP + TN) / Total = (150 + 200) / 500 = 350 / 500 = 0.70 (70%)

Precision = TP / (TP + FP) = 150 / (150 + 100) = 150 / 250 = 0.60 (60%)

Recall = TP / (TP + FN) = 150 / (150 + 50) = 150 / 200 = 0.75 (75%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.60 x 0.75 / (0.60 + 0.75) = 0.9 / 1.35 = 0.67

(iii)

Precision, because a stranger accepted as the owner (False Positive) can open the phone.

C2.12Practice4 marks

A regression model predicts the rainfall (in mm). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual1579383121
Predicted1589478118
Answer
(i)
CaseActualPredictedError
1157158-1
29394-1
383785
41211183
(ii)

Squared errors: (-1)2 = 1, (-1)2 = 1, (5)2 = 25, (3)2 = 9

(iii)

MSE = sum of squared errors / number of cases = (1 + 1 + 25 + 9) / 4 = 36 / 4 = 9

(iv)

RMSE = square root of MSE = square root of 9 = 3

C2.13Practice4 marks

The confusion matrix of a flood-warning model, tested on 1000 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: floodReality: no flood
Predicted: flood260TP140FP
Predicted: no flood260FN340TN
Answer
(i)

Accuracy = (TP + TN) / Total = (260 + 340) / 1000 = 600 / 1000 = 0.60 (60%)

(ii)

Precision = TP / (TP + FP) = 260 / (260 + 140) = 260 / 400 = 0.65 (65%)

(iii)

Recall = TP / (TP + FN) = 260 / (260 + 260) = 260 / 520 = 0.50 (50%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.65 x 0.50 / (0.65 + 0.50) = 0.65 / 1.15 = 0.57

C2.14Practice4 marks

A regression model predicts the height of plants (in cm). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual51287971
Predicted48197670
Answer
(i)
CaseActualPredictedError
151483
228199
379763
471701
(ii)

Squared errors: (3)2 = 9, (9)2 = 81, (3)2 = 9, (1)2 = 1

(iii)

MSE = sum of squared errors / number of cases = (9 + 81 + 9 + 1) / 4 = 100 / 4 = 25

(iv)

RMSE = square root of MSE = square root of 25 = 5

C2.15Practice4 marks

An AI that finds pneumonia in chest X-rays was tested on 50 cases. It predicted 'pneumonia' for 25 cases; out of these, 24 were really 'pneumonia'. It predicted 'normal' for the other 25 cases; out of these, 19 were really 'normal'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 24, FP = 25 - 24 = 1, TN = 19, FN = 25 - 19 = 6.

Confusion matrix

Reality: pneumoniaReality: normal
Predicted: pneumonia24TP1FP
Predicted: normal6FN19TN
(ii)

Accuracy = (TP + TN) / Total = (24 + 19) / 50 = 43 / 50 = 0.86 (86%)

Precision = TP / (TP + FP) = 24 / (24 + 1) = 24 / 25 = 0.96 (96%)

Recall = TP / (TP + FN) = 24 / (24 + 6) = 24 / 30 = 0.80 (80%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.96 x 0.80 / (0.96 + 0.80) = 1.536 / 1.76 = 0.87

(iii)

Recall, because a patient whose pneumonia is missed (False Negative) goes untreated.

C2.16Practice4 marks

A regression model predicts the weight of parcels (in kg). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual11465357
Predicted6534856
Answer
(i)
CaseActualPredictedError
11165
24653-7
353485
457561
(ii)

Squared errors: (5)2 = 25, (-7)2 = 49, (5)2 = 25, (1)2 = 1

(iii)

MSE = sum of squared errors / number of cases = (25 + 49 + 25 + 1) / 4 = 100 / 4 = 25

(iv)

RMSE = square root of MSE = square root of 25 = 5

C2.17Practice4 marks

The confusion matrix of a filter that blocks unsafe videos for children, tested on 100 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: unsafe videoReality: safe video
Predicted: unsafe video24TP6FP
Predicted: safe video16FN54TN
Answer
(i)

Accuracy = (TP + TN) / Total = (24 + 54) / 100 = 78 / 100 = 0.78 (78%)

(ii)

Precision = TP / (TP + FP) = 24 / (24 + 6) = 24 / 30 = 0.80 (80%)

(iii)

Recall = TP / (TP + FN) = 24 / (24 + 16) = 24 / 40 = 0.60 (60%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.80 x 0.60 / (0.80 + 0.60) = 0.96 / 1.40 = 0.69

C2.18Practice4 marks

A regression model predicts the units of electricity used. The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual115149110117
Predicted116148103110
Answer
(i)
CaseActualPredictedError
1115116-1
21491481
31101037
41171107
(ii)

Squared errors: (-1)2 = 1, (1)2 = 1, (7)2 = 49, (7)2 = 49

(iii)

MSE = sum of squared errors / number of cases = (1 + 1 + 49 + 49) / 4 = 100 / 4 = 25

(iv)

RMSE = square root of MSE = square root of 25 = 5

C2.19Practice4 marks

A camera that finds defective bottles in a factory was tested on 200 cases. It predicted 'defective bottle' for 120 cases; out of these, 84 were really 'defective bottle'. It predicted 'good bottle' for the other 80 cases; out of these, 24 were really 'good bottle'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 84, FP = 120 - 84 = 36, TN = 24, FN = 80 - 24 = 56.

Confusion matrix

Reality: defective bottleReality: good bottle
Predicted: defective bottle84TP36FP
Predicted: good bottle56FN24TN
(ii)

Accuracy = (TP + TN) / Total = (84 + 24) / 200 = 108 / 200 = 0.54 (54%)

Precision = TP / (TP + FP) = 84 / (84 + 36) = 84 / 120 = 0.70 (70%)

Recall = TP / (TP + FN) = 84 / (84 + 56) = 84 / 140 = 0.60 (60%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.70 x 0.60 / (0.70 + 0.60) = 0.84 / 1.30 = 0.65

(iii)

Recall, because a defective bottle that is passed (False Negative) reaches the customer.

C2.20Practice4 marks

A regression model predicts the time taken for delivery (in minutes). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual36504727
Predicted40464331
Answer
(i)
CaseActualPredictedError
13640-4
250464
347434
42731-4
(ii)

Squared errors: (-4)2 = 16, (4)2 = 16, (4)2 = 16, (-4)2 = 16

(iii)

MSE = sum of squared errors / number of cases = (16 + 16 + 16 + 16) / 4 = 64 / 4 = 16

(iv)

RMSE = square root of MSE = square root of 16 = 4

C2.21Practice4 marks

The confusion matrix of a disease-screening AI, tested on 1000 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: has the diseaseReality: is healthy
Predicted: has the disease120TP40FP
Predicted: is healthy180FN660TN
Answer
(i)

Accuracy = (TP + TN) / Total = (120 + 660) / 1000 = 780 / 1000 = 0.78 (78%)

(ii)

Precision = TP / (TP + FP) = 120 / (120 + 40) = 120 / 160 = 0.75 (75%)

(iii)

Recall = TP / (TP + FN) = 120 / (120 + 180) = 120 / 300 = 0.40 (40%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.75 x 0.40 / (0.75 + 0.40) = 0.6 / 1.15 = 0.52

C2.22Practice4 marks

A regression model predicts the marks of students. The actual and the predicted values of 3 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case123
Actual718841
Predicted708342
Answer
(i)
CaseActualPredictedError
171701
288835
34142-1
(ii)

Squared errors: (1)2 = 1, (5)2 = 25, (-1)2 = 1

(iii)

MSE = sum of squared errors / number of cases = (1 + 25 + 1) / 3 = 27 / 3 = 9

(iv)

RMSE = square root of MSE = square root of 9 = 3

C2.23Practice4 marks

A spam filter was tested on 200 cases. It predicted 'spam' for 112 cases; out of these, 84 were really 'spam'. It predicted 'genuine mail' for the other 88 cases; out of these, 32 were really 'genuine mail'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 84, FP = 112 - 84 = 28, TN = 32, FN = 88 - 32 = 56.

Confusion matrix

Reality: spamReality: genuine mail
Predicted: spam84TP28FP
Predicted: genuine mail56FN32TN
(ii)

Accuracy = (TP + TN) / Total = (84 + 32) / 200 = 116 / 200 = 0.58 (58%)

Precision = TP / (TP + FP) = 84 / (84 + 28) = 84 / 112 = 0.75 (75%)

Recall = TP / (TP + FN) = 84 / (84 + 56) = 84 / 140 = 0.60 (60%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.75 x 0.60 / (0.75 + 0.60) = 0.9 / 1.35 = 0.67

(iii)

Precision, because a genuine mail sent to the spam folder (False Positive) may be an important message.

C2.24Practice4 marks

A regression model predicts the price of houses (in lakh rupees). The actual and the predicted values of 3 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case123
Actual346441
Predicted416536
Answer
(i)
CaseActualPredictedError
13441-7
26465-1
341365
(ii)

Squared errors: (-7)2 = 49, (-1)2 = 1, (5)2 = 25

(iii)

MSE = sum of squared errors / number of cases = (49 + 1 + 25) / 3 = 75 / 3 = 25

(iv)

RMSE = square root of MSE = square root of 25 = 5

C2.25Practice4 marks

The confusion matrix of a forest-fire alert system, tested on 100 cases, is given below. Calculate:

  1. Accuracy
  2. Precision
  3. Recall and
  4. F1 score. Show the working.

Confusion matrix

Reality: fireReality: no fire
Predicted: fire36TP24FP
Predicted: no fire14FN26TN
Answer
(i)

Accuracy = (TP + TN) / Total = (36 + 26) / 100 = 62 / 100 = 0.62 (62%)

(ii)

Precision = TP / (TP + FP) = 36 / (36 + 24) = 36 / 60 = 0.60 (60%)

(iii)

Recall = TP / (TP + FN) = 36 / (36 + 14) = 36 / 50 = 0.72 (72%)

(iv)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.60 x 0.72 / (0.60 + 0.72) = 0.864 / 1.32 = 0.65

C2.26Practice4 marks

A regression model predicts the daily temperature (in Celsius). The actual and the predicted values of 3 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case123
Actual273127
Predicted254129
Answer
(i)
CaseActualPredictedError
127252
23141-10
32729-2
(ii)

Squared errors: (2)2 = 4, (-10)2 = 100, (-2)2 = 4

(iii)

MSE = sum of squared errors / number of cases = (4 + 100 + 4) / 3 = 108 / 3 = 36

(iv)

RMSE = square root of MSE = square root of 36 = 6

C2.27Practice4 marks

A bank's fraud detector was tested on 100 cases. It predicted 'fraud' for 30 cases; out of these, 24 were really 'fraud'. It predicted 'genuine transaction' for the other 70 cases; out of these, 54 were really 'genuine transaction'.

  1. Draw the confusion matrix.
  2. Calculate accuracy, precision, recall and F1 score.
  3. Which metric is more important for this system, precision or recall? Why?
Answer
(i)

TP = 24, FP = 30 - 24 = 6, TN = 54, FN = 70 - 54 = 16.

Confusion matrix

Reality: fraudReality: genuine transaction
Predicted: fraud24TP6FP
Predicted: genuine transaction16FN54TN
(ii)

Accuracy = (TP + TN) / Total = (24 + 54) / 100 = 78 / 100 = 0.78 (78%)

Precision = TP / (TP + FP) = 24 / (24 + 6) = 24 / 30 = 0.80 (80%)

Recall = TP / (TP + FN) = 24 / (24 + 16) = 24 / 40 = 0.60 (60%)

F1 score = 2 x Precision x Recall / (Precision + Recall) = 2 x 0.80 x 0.60 / (0.80 + 0.60) = 0.96 / 1.40 = 0.69

(iii)

Recall, because a fraud that is missed (False Negative) causes a loss of money.

C2.28Practice4 marks

A regression model predicts the sales of a shop (in thousand rupees). The actual and the predicted values of 3 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case123
Actual1155092
Predicted1134890
Answer
(i)
CaseActualPredictedError
11151132
250482
392902
(ii)

Squared errors: (2)2 = 4, (2)2 = 4, (2)2 = 4

(iii)

MSE = sum of squared errors / number of cases = (4 + 4 + 4) / 3 = 12 / 3 = 4

(iv)

RMSE = square root of MSE = square root of 4 = 2

C2.29Practice4 marks

A regression model predicts the runs scored by a batter. The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual36214874
Predicted38235076
Answer
(i)
CaseActualPredictedError
13638-2
22123-2
34850-2
47476-2
(ii)

Squared errors: (-2)2 = 4, (-2)2 = 4, (-2)2 = 4, (-2)2 = 4

(iii)

MSE = sum of squared errors / number of cases = (4 + 4 + 4 + 4) / 4 = 16 / 4 = 4

(iv)

RMSE = square root of MSE = square root of 4 = 2

C2.30Practice4 marks

A regression model predicts the rainfall (in mm). The actual and the predicted values of 4 cases are given below.

  1. Find the error (actual - predicted) of each case.
  2. Find the squared errors.
  3. Calculate the Mean Squared Error (MSE).
  4. Calculate the Root Mean Squared Error (RMSE).
Case1234
Actual6417319369
Predicted6417719369
Answer
(i)
CaseActualPredictedError
164640
2173177-4
31931930
469690
(ii)

Squared errors: (0)2 = 0, (-4)2 = 16, (0)2 = 0, (0)2 = 0

(iii)

MSE = sum of squared errors / number of cases = (0 + 16 + 0 + 0) / 4 = 16 / 4 = 4

(iv)

RMSE = square root of MSE = square root of 4 = 2

C3Neuron (perceptron) numericals4 marks · 12 questions
C3.1Practice4 marks

A single neuron (perceptron) is used to decide: "Should Riya go to the park?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
The weather is good3Yes (1)No (0)
Her friend is coming5No (0)Yes (1)
Her homework is done1No (0)Yes (1)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 3) + (0 x 5) + (0 x 1) + (-1) = 2. It is less than 4, so the output is 0 (No).

(iii)

Sum = (0 x 3) + (1 x 5) + (1 x 1) + (-1) = 5. It is not less than 4, so the output is 1 (Yes).

(iv)

Her friend is coming, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.2Practice4 marks

A single neuron (perceptron) is used to decide: "Should Arjun buy the phone?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 3 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
The price is within budget2No (0)Yes (1)
The camera is good1Yes (1)No (0)
The reviews are good5Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (0 x 2) + (1 x 1) + (1 x 5) + (-1) = 5. It is not less than 3, so the output is 1 (Yes).

(iii)

Sum = (1 x 2) + (0 x 1) + (0 x 5) + (-1) = 1. It is less than 3, so the output is 0 (No).

(iv)

The reviews are good, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.3Practice4 marks

A single neuron (perceptron) is used to decide: "Should the school team play the match?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
The ground is dry3Yes (1)Yes (1)
All the players are fit5Yes (1)No (0)
The coach is present1Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 3) + (1 x 5) + (1 x 1) + (-1) = 8. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (1 x 3) + (0 x 5) + (0 x 1) + (-1) = 2. It is less than 4, so the output is 0 (No).

(iv)

All the players are fit, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.4Practice4 marks

A single neuron (perceptron) is used to decide: "Should Meena watch the film?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is 1. The output is 1 (Yes) if the weighted sum is 6 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
Her exam is over1Yes (1)No (0)
Her friends are going5No (0)Yes (1)
The ticket is cheap4Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 1) + (0 x 5) + (1 x 4) + (1) = 6. It is not less than 6, so the output is 1 (Yes).

(iii)

Sum = (0 x 1) + (1 x 5) + (0 x 4) + (1) = 6. It is not less than 6, so the output is 1 (Yes).

(iv)

Her friends are going, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.5Practice4 marks

A single neuron (perceptron) is used to decide: "Should the farmer water the field today?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -2. The output is 1 (Yes) if the weighted sum is 3 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
The soil is dry1Yes (1)No (0)
No rain is forecast5No (0)Yes (1)
The pump has power3No (0)Yes (1)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 1) + (0 x 5) + (0 x 3) + (-2) = -1. It is less than 3, so the output is 0 (No).

(iii)

Sum = (0 x 1) + (1 x 5) + (1 x 3) + (-2) = 6. It is not less than 3, so the output is 1 (Yes).

(iv)

No rain is forecast, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.6Practice4 marks

A single neuron (perceptron) is used to decide: "Should Kabir join the coding club?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is 1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
He is free on that day3Yes (1)No (0)
He likes coding1No (0)Yes (1)
His friend has joined2No (0)Yes (1)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 3) + (0 x 1) + (0 x 2) + (1) = 4. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (0 x 3) + (1 x 1) + (1 x 2) + (1) = 4. It is not less than 4, so the output is 1 (Yes).

(iv)

He is free on that day, because it has the largest weight (3). A larger weight means the input has more effect on the decision.

C3.7Practice4 marks

A single neuron (perceptron) is used to decide: "Should the family go on a picnic?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
It is a holiday2No (0)Yes (1)
The weather is clear4Yes (1)No (0)
The car is available1Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (0 x 2) + (1 x 4) + (1 x 1) + (-1) = 4. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (1 x 2) + (0 x 4) + (0 x 1) + (-1) = 1. It is less than 4, so the output is 0 (No).

(iv)

The weather is clear, because it has the largest weight (4). A larger weight means the input has more effect on the decision.

C3.8Practice4 marks

A single neuron (perceptron) is used to decide: "Should Sana order food online?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is 1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
She is very hungry4Yes (1)No (0)
There is a discount1Yes (1)No (0)
Delivery is fast2No (0)Yes (1)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 4) + (1 x 1) + (0 x 2) + (1) = 6. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (0 x 4) + (0 x 1) + (1 x 2) + (1) = 3. It is less than 4, so the output is 0 (No).

(iv)

She is very hungry, because it has the largest weight (4). A larger weight means the input has more effect on the decision.

C3.9Practice4 marks

A single neuron (perceptron) is used to decide: "Should the shop open on Sunday?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
Many customers are expected2Yes (1)No (0)
Staff is available3Yes (1)No (0)
It is a festival week4No (0)Yes (1)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 2) + (1 x 3) + (0 x 4) + (-1) = 4. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (0 x 2) + (0 x 3) + (1 x 4) + (-1) = 3. It is less than 4, so the output is 0 (No).

(iv)

It is a festival week, because it has the largest weight (4). A larger weight means the input has more effect on the decision.

C3.10Practice4 marks

A single neuron (perceptron) is used to decide: "Should Dev go for the morning run?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
He slept well1No (0)Yes (1)
It is not raining4No (0)Yes (1)
His shoes are dry5Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (0 x 1) + (0 x 4) + (1 x 5) + (-1) = 4. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (1 x 1) + (1 x 4) + (0 x 5) + (-1) = 4. It is not less than 4, so the output is 1 (Yes).

(iv)

His shoes are dry, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.11Practice4 marks

A single neuron (perceptron) is used to decide: "Should the class go on the science trip?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
Parents have agreed4No (0)Yes (1)
The bus is booked5Yes (1)No (0)
The museum is open1Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (0 x 4) + (1 x 5) + (1 x 1) + (-1) = 5. It is not less than 4, so the output is 1 (Yes).

(iii)

Sum = (1 x 4) + (0 x 5) + (0 x 1) + (-1) = 3. It is less than 4, so the output is 0 (No).

(iv)

The bus is booked, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

C3.12Practice4 marks

A single neuron (perceptron) is used to decide: "Should Tara adopt the puppy?" Each factor is an input: Yes = 1, No = 0. The weights are given in the table. The bias is -1. The output is 1 (Yes) if the weighted sum is 4 or more, otherwise 0 (No).

  1. Write the formula of the weighted sum.
  2. Calculate the weighted sum and the decision for Day 1.
  3. Calculate them for Day 2.
  4. Which factor matters the most to this neuron? Why?
Factor (input)WeightDay 1Day 2
She has time for it2Yes (1)No (0)
Her parents agree5No (0)Yes (1)
There is space at home1Yes (1)No (0)
Answer
(i)

Weighted sum = (x1 x w1) + (x2 x w2) + (x3 x w3) + bias

(ii)

Sum = (1 x 2) + (0 x 5) + (1 x 1) + (-1) = 2. It is less than 4, so the output is 0 (No).

(iii)

Sum = (0 x 2) + (1 x 5) + (0 x 1) + (-1) = 4. It is not less than 4, so the output is 1 (Yes).

(iv)

Her parents agree, because it has the largest weight (5). A larger weight means the input has more effect on the decision.

CEEmployability skills: 4-mark practice answers (5 per unit)4 marks · 25 questions
CE.1Practice4 marks

Explain the five stages of active listening with an example.

Answer

Receiving - hearing the message ('take one tablet twice a day'); Understanding - interpreting it (morning and night); Remembering - storing it (note in the phone); Evaluating - judging it ('before or after food?'); Responding - feedback (asking the doctor, nodding).

CE.2Practice4 marks

Explain RESPECT, the guide to active listening.

Answer

R - Remove distractions; E - Eye contact; S - Show you are listening by nodding; P - Pay attention; E - Empathise with the speaker; C - Clarify doubts by asking or paraphrasing; T - Tune yourself to the speaker's pace and tone.

CE.3Practice4 marks

Write any four barriers to active listening and how to overcome them.

Answer

Distractions - keep the phone away; prejudice - keep an open mind; interrupting - let the speaker finish; daydreaming - focus and take notes; preparing your reply too early - listen fully first; information overload - ask for key points.

CE.4Practice4 marks

Change the voice:

  1. The chef cooked the meal.
  2. He is painting the wall.
  3. The shop will be opened by them.
  4. She writes reports.
Answer

(i) The meal was cooked by the chef. (ii) The wall is being painted by him. (iii) They will open the shop. (iv) Reports are written by her.

CE.5Practice4 marks

Explain the five types of nouns with examples.

Answer

Proper - India, Ravi; Common - city, boy; Collective - team, herd; Abstract - honesty, courage; Material - gold, wood, cotton.

CE.6Practice4 marks

Explain Maslow's hierarchy of needs.

Answer

From the base: physiological needs (food, water, sleep); safety (security, job, health); love and belonging (family, friends); esteem (respect, recognition); self-actualisation (reaching full potential). Lower needs must be met before higher needs motivate us.

CE.7Practice4 marks

What is result orientation? Explain its steps with an example.

Answer

Result orientation is focusing on achieving the desired outcome. Steps: set a clear goal, make an action plan, use the right tools, work within the time, measure the result and improve. Example: a student aiming for 90 in AI plans chapters weekly, practises questions and tracks sample-paper scores.

CE.8Practice4 marks

Explain the Big Five personality factors with workplace examples.

Answer

Openness - a designer trying new styles; Conscientiousness - an accountant meeting deadlines; Extraversion - a salesperson who loves meeting people; Agreeableness - a caring nurse; Neuroticism - low neuroticism helps an air-traffic controller stay calm.

CE.9Practice4 marks

Write any four ways to maintain a positive attitude.

Answer

Practise gratitude; use positive self-talk; keep positive company; follow a healthy routine of exercise, sleep and food; focus on solutions; help others. (Any four.)

CE.10Practice4 marks

What is self-awareness? Explain its aspects and ways to develop it.

Answer

Self-awareness is a clear understanding of one's personality, strengths, weaknesses, emotions and values. Aspects: strengths, weaknesses, emotions and their triggers, values. Ways: reflection and journaling, feedback from others, personality tests, meditation and new experiences.

CE.11Practice4 marks

Write the result of each formula if A1 = 20, A2 = 30, A3 = 50: =SUM(A1:A3), =AVERAGE(A1:A3), =MAX(A1:A3), =MIN(A1:A3).

Answer

=SUM gives 100; =AVERAGE gives 33.33; =MAX gives 50; =MIN gives 20.

CE.12Practice4 marks

Differentiate between relative, absolute and mixed cell references.

Answer

Relative (A1) changes when the formula is copied; absolute ($A$1) never changes; mixed ($A1 or A$1) keeps either the column or the row fixed. Absolute references are used for fixed values like a tax rate.

CE.13Practice4 marks

Differentiate between sorting and filtering and write the steps for each.

Answer

Sorting arranges all rows in order: select data > Data > Sort > choose column and order. Filtering shows only rows meeting a condition and hides others: Data > AutoFilter > click the arrow > choose the condition. Filtering does not delete data.

CE.14Practice4 marks

Name four chart types and when to use each.

Answer

Column/bar - compare items; line - trend over time; pie - parts of a whole; scatter - relation between two variables.

CE.15Practice4 marks

Explain any four features of presentation software.

Answer

Slide layouts - title, content, two content; slide master - same design on all slides; transitions - effects between slides; animations - effects on objects; speaker notes; slide sorter view; F5 to start the slide show.

CE.16Practice4 marks

Explain any four types of entrepreneurs with examples.

Answer

Service - salon, courier; Business/trading - grocery, wholesale; Industrial - textile mill, food processing; Agricultural - dairy, poultry; Technical - software or app company; Social - affordable healthcare or solar lighting. (Any four.)

CE.17Practice4 marks

Explain the entrepreneurial competencies with examples.

Answer

Decisiveness - chooses a supplier after comparing quotes; Initiative - starts home delivery before competitors; Interpersonal skills - keeps customers and staff happy; Perseverance - relaunches after a failed product; Organisational skills - manages stock, cash and staff schedules.

CE.18Practice4 marks

What is a business plan? Explain its main parts.

Answer

A business plan is a written document describing the business idea, market, operations and finances. Parts: executive summary, business description, market analysis, products and services, marketing plan (4 Ps), operations plan and financial plan.

CE.19Practice4 marks

A candle maker has fixed costs of Rs 15,000 a month. Each candle sells for Rs 40 and costs Rs 25 to make. Find the break-even point. What happens if she sells 1,200 candles?

Answer

Break-even = 15,000 / (40 - 25) = 15,000 / 15 = 1,000 candles. At 1,200 candles, profit = 200 x 15 = Rs 3,000 (the contribution of each candle beyond break-even).

CE.20Practice4 marks

Explain the barriers to entrepreneurship and ways to overcome them.

Answer

Environmental - poor roads, power, raw material; choose a suitable location. No/faulty business plan; prepare one with market research. Personal - self-doubt, fear of failure; training and mentors. Financial - lack of capital; savings, Mudra loans, investors.

CE.21Practice4 marks

What are green jobs? Explain any four fields of green jobs.

Answer

Green jobs protect or restore the environment. Agriculture - organic farming advisor; transport - EV technician; renewable energy - solar PV installer; water conservation - rainwater harvesting technician; waste management - recycling supervisor; green construction - green building consultant.

CE.22Practice4 marks

Explain the benefits of green jobs.

Answer

They limit greenhouse-gas emissions, reduce waste and pollution, protect and restore ecosystems, use energy and raw materials efficiently, help communities adapt to climate change, and create decent employment.

CE.23Practice4 marks

Explain how climate change happens and name the main greenhouse gases.

Answer

Burning fossil fuels and cutting forests increase greenhouse gases, which trap more heat, causing global warming and climate change - floods, droughts, heatwaves and sea-level rise. Main gases: carbon dioxide, methane, nitrous oxide, water vapour and fluorinated gases.

CE.24Practice4 marks

Write any four missions of the NAPCC and their focus.

Answer

National Solar Mission - solar energy; Enhanced Energy Efficiency - saving energy; Sustainable Habitat - green cities and transport; National Water Mission - water conservation; Green India - afforestation; Sustainable Agriculture - climate-resilient farming.

CE.25Practice4 marks

Explain the different levels of green skills with examples.

Answer

Green citizens - everyone saving energy and segregating waste; green workers - waste collectors and plant operators; green technicians - solar installers and energy auditors; green experts - scientists and planners who design green policies and technologies.

CVComputer vision: more 4-mark answers4 marks · 5 questions
CV.1Practice4 marks

Explain the stages of the computer vision process with the example of number-plate recognition.

Answer

Image acquisition - toll camera captures the car; pre-processing - resize, remove noise, adjust contrast, grayscale; feature extraction - find edges and characters; detection/segmentation - cut out the plate region; high-level processing - read characters and charge the toll.

CV.2Practice4 marks

Differentiate between human vision and computer vision.

Answer

Human vision captures light with eyes and the brain recognises objects instantly using experience and context, but tires. Computer vision captures pixels with cameras and uses algorithms trained on many labelled images; it works at large scale 24x7 but can fail with unusual lighting or angles.

CV.3Practice4 marks

Explain any four challenges of computer vision.

Answer

Lighting changes alter pixel values; occlusion - objects partly hidden; different viewpoints and scale; cluttered backgrounds; the need for huge labelled datasets; bias in datasets; privacy concerns. (Any four.)

CV.4Practice4 marks

Explain any four computer-vision tasks with examples.

Answer

Image classification - label the whole image; object detection - boxes around many objects; image segmentation - label every pixel; face recognition - identify a person; OCR - read text; object tracking - follow objects in video; pose estimation - find body joints. (Any four.)

CV.5Practice4 marks

A colour image is 1920 x 1080 pixels. Find the number of pixels and the memory needed at 3 bytes per pixel. Why is pre-processing needed?

Answer

Pixels = 1920 x 1080 = 2,073,600. Memory = 3 x 2,073,600 = 6,220,800 bytes, about 6.2 MB. Pre-processing (resizing, grayscale, noise removal, contrast adjustment) reduces size and noise so that features can be found faster and more accurately.

11

Flashcards for one-mark questions

Tap an option to check your answer at once; your score is saved

Quick quiz: 10 MCQs

Ten multiple-choice questions picked at random. Tap an option to answer. You get your score at the end.

12

Practice question papers

Fifteen ready papers with blueprints and a random paper maker, all on the design of the CBSE Sample Question Paper 2026-27

15 Sample Question Papers (CBSE pattern, 50 marks, 2 hours)

Each paper has 21 questions for 50 marks and 2 hours, with the same choices as the CBSE Sample Question Paper 2026-27: any 4 of 6 in Q1, any 5 of 6 in Q2 to Q5, any 3 of Q6 to Q10, any 4 of Q11 to Q16 and any 3 of Q17 to Q21. Every paper has numericals in Section A, and a confusion matrix or RMSE numerical in Q17 to Q21. No question is repeated: the fifteen papers use 690 different questions.

Or make a fresh random paper

Marking scheme, download and timer

Blueprint only:
02:00:00

Choose Paper 1 to Paper 15, or make a random paper. The blueprint and the paper open here.

13

Last-day checklist

Read this the evening before and again at the exam centre gate

Before the paper

  • Write from memory: the 10 steps of the methodology, the 5 stages of computer vision, the 6 Vs, the 4 steps of Big Data analytics, Freytag's Pyramid.
  • Write the formulas once: accuracy, precision, recall, F1, MSE, RMSE.
  • Revise the five Employability Skills tables.

In the first 10 minutes

  • In Q1 to Q5, tick the parts you are sure of: 4 of 6 in Q1, 5 of 6 in the others.
  • From Q17 to Q21 choose the three you can write in points.

While writing

  • Attempt the questions of a section in order.
  • Write long answers in points with headings and one example.
  • In numericals, write the formula, put the values, then the answer.
Marks katne wali galti
  • Mixing Veracity, Velocity and Variety
  • Writing edge detection under preprocessing
  • Writing FN in place of FP in precision
  • Forgetting the square root in RMSE
  • Answering more parts than asked: only the first ones are checked