CBSE Class 10 Question Paper 2026 Solution Artificial Intelligence

FOR CBSE CLASS 10 EXAM PREPARATION

CBSE Class 10 2026
Question Paper
Solution · Artificial
Intelligence
EXAM YEAR TYPE SUBJECT

CBSE Class 10 2026 Question Paper Solution Artificial Intelligence

Notes · Sample Papers · Previous Year Papers · Mock Tests

.
.co s e m

s em g l a
a Marking Scheme
Strictly Confidential a
(For Internal and Restricted use only)
Secondary School Examination, 2026 (Xth)

SUBJECT NAME : Artificial Intelligence (417) (Q.P. CODE /Set No. 104/4)

General Instructions: -

You are aware that evaluation is the most important process in the actual and
m
1
om
correct assessment of the candidates. A small mistake in evaluation may lead to
. co
c
serious problems which may affect the future of the candidates, education
. e m
e m
system and teaching profession. To avoid mistakes, it is requested that before
l as
l as
starting evaluation, you must read and understand the spot evaluation guidelines
carefully.
ag
2 ag
“Evaluation policy is a confidential policy as it is related to the confidentiality
of the examinations conducted, evaluation done and several other aspects.
Its leakage to public in any manner could lead to derailment of the
examination system and affect the life and future of millions of candidates.
Sharing this policy/document to anyone, publishing in any magazine and
printing in Newspaper/Website, etc. may invite action under various rules of
the Board and IPC.”
Evaluation is to be done as per instructions provided in the Marking Scheme. It
3 should not be done according to one’s own interpretation or any other
m
.co
consideration. Marking Scheme should be strictly adhered to and religiously
followed. However, while evaluating, answers which are based on latest

e m
information or knowledge and/or are innovative, they may be assessed for

as
their correctness otherwise and due marks be awarded to them. In Class-X,
l
ag
while evaluating two competency-based questions, please try to understand
given answer and even if reply is not from marking scheme but correct
competency is enumerated by the candidate, due marks should be awarded.

The Marking scheme carries only suggested value points for the answers.
4 These are in the nature of Guidelines only and do not constitute the complete
answer. The students can have their own expression and if the expression is
correct, the due marks should be awarded accordingly.
The Head-Examiner must go through the first five answer books evaluated by
5 each evaluator on the first day, to ensure that evaluation has been carried out as
m
.co
per the instructions given in the Marking Scheme. If there is any variation, the
m
.co m
same should be zero after deliberation and discussion. The remaining answer

m
books meant for evaluation shall be given only after ensuring that there is no
s e
s e significant variation in the marking of individual evaluators.
g la
g la a
Evaluators will mark ( √ ) wherever answer is correct. For wrong answer CROSS

a 6 ‘X’ be marked. Evaluators will not put right (✓) while evaluating which gives an
impression that answer is correct and no marks are awarded. This is most
common mistake which evaluators are committing.
If a question has parts, please award marks on the right-hand side for each part.
7 Marks awarded for different parts of the question should then be totaled up and
written in the left-hand margin and encircled. This may be followed strictly.

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 1/22]

e m
em as
s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl
Page 1 of 22

If a question does not have any parts, marks must be awarded in the left-hand
8 margin and encircled. This may also be followed strictly.

If a student has attempted an extra question, answer of the question deserving
9 more marks should be retained and the other answer scored out with a note
“Extra Question”.
No marks to be deducted for the cumulative effect of an error. It should be
10 penalized only once.

A full scale of marks 50 has to be used. Please do not hesitate to award full
11 marks if the answer deserves it.

Every examiner has to necessarily do evaluation work for full working hours i.e.,
12 8 hours every day and evaluate 20 answer books per day in main subjects and 25
answer books per day in other subjects (Details are given in Spot Guidelines).This
is in view of the reduced syllabus and number of questions in question paper.
Ensure that you do not make the following common types of errors committed by
13 the Examiner in the past:-
● Leaving answer or part thereof unassessed in an answer book.
● Giving more marks for an answer than assigned to it.
● Wrong totaling of marks awarded on an answer.
● Wrong transfer of marks from the inside pages of the answer book to the
title page.
● Wrong question wise totaling on the title page.
● Wrong totaling of marks of the two columns on the title page.
● Wrong grand total.
● Marks in words and figures not tallying/not same.
● Wrong transfer of marks from the answer book to online award list.
● Answers marked as correct, but marks not awarded. (Ensure that the right
tick mark is correctly and clearly indicated. It should merely be a line.
Same is with the X for incorrect answers.)
● Half or a part of the answer marked correct and the rest as wrong, but no
marks awarded.
While evaluating the answer books, if the answer is found to be totally incorrect,
14 it should be marked as cross (X) and awarded zero (0)Marks.

Any unassessed portion, non-carrying over of marks to the title page, or totaling
15 error detected by the candidate shall damage the prestige of all the personnel
engaged in the evaluation work as also of the Board. Hence, in order to uphold
the prestige of all concerned, it is again reiterated that the instructions be
followed meticulously and judiciously.
The Examiners should acquaint themselves with the guidelines given in the
16 “Guidelines for Spot Evaluation” before starting the actual evaluation.

Every Examiner shall also ensure that all the answers are evaluated, marks
17 carried over to the title page, correctly totaled and written in figures and words.

The candidates are entitled to obtain a photocopy of the Answer Book on request
18 on payment of the prescribed processing fee. All Examiners/Additional Head
Examiners/Head Examiners are once again reminded that they must ensure that
evaluation is carried out strictly as per value points for each answer as given in
the Marking Scheme.

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 2/22]
​
​
​
​
​
​
​
​
​
​
​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 2 of 22

.
.co s e m

s em l a
a ag
General Instructions:
(i) Please read the instructions carefully.
(ii) This Question Paper consists of 21 questions in two sections:Section-A &
Section-B.
(iii) Section-A has Objective Type Questions, whereas Section- B contains o m
m . c
. co
Subjective Type Questions.
s e m
em (5 + 16) = 21 questions, a candidate has to answer (5+10) = 15 gla
(iv) Out of the given
s
g
questionslain the allotted (maximum) time of 2 hours. a
a
(v) All questions of a particular section must be attempted in the correct order.
(vi) SECTION-A: Objective Type Questions (24 Marks):
(a) This section has 5 questions.
(b) There is no negative marking.
(c) Do as per the instructions given.
m
.co
(d) Marks allotted are mentioned against each question/part.
m
e
(vii) SECTION -B: Subjective Type Questions (26 Marks):
s
g l a
(a) This section has 16 questions.
a
(b) A candidate has to do 10 questions.
(c) Do as per the instructions given.
(d) Marks allotted are mentioned against each question/part.

SECTION - A
m
(Objective Type Questions)
o
m c
. :
1.
c. o Answer any 4 out of the given 6 questions on Employability s e mskills 4x1=4
m
e (i) Identify the imperative sentence: l a
las a g 1

ag (A) Shut the front door. (B) She is talented artist.
(C) Are you feeling better ? (D) You were amazing !

Ans (A)
OR
Shut the front door.

m . c
​

c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 3/22]

e m
​
​
​

s
​

em
​

a
​
​

gl
​

s
For more Question Papers, Sample Papers, Notes & Syllabus visit Page 3 of 22

(1 Mark for the correct answer)

(ii) Breaking down big goals into smaller parts will make the goal _________. 1

(A) specific (B) measurable
(C) achievable (D) realistic

Ans (C)
OR
achievable

(1 Mark for the correct answer)

(iii) Define the term ‘Time Management’. 1

Ans Time management is the ability to plan and control how you spend the
hours of your day well and do all that you want to do.
OR
Prioritise the things you have to do.
OR
Remove waste and redundancy from work.
OR
Make a time table and follow it diligently.

(1 Mark for any correct/relevant answer)

(iv) What should a strong password consist of ? 1
(A) Only letters
(B) Numbers and special characters
(C) Name of a person
(D) Letters, numbers and special characters

Ans (D)
OR
Letters, numbers and special characters

(1 Mark for the correct answer)

(v) A misconception about an entrepreneur is : 1
Entrepreneurs are ___________, not __________.

Ans born , made
OR
rich, poor

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 4/22]

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 4 of 22

.
.co s e m

s em OR
l a
a unique, common
OR
ag
big businessmen, small businessmen

(1 Mark for any correct / relevant answer)

(vi) Choose the option which is NOT a Sustainable Development Goal 1
according to United Nations.

m
co
(A) Population (B) No poverty
m .
c. o
(C) Quality education (D) Reduced Inequalities
s e m
(A) se
m l a
Ans
ORla ag
g
aPopulation
(1 Mark for the correct answer)

2. Answer any 5 out of the given 6 questions : 5X1=5

(i) Anita and Surjit are creating an AI application that will classify different 1
types of fruits. The Computer Vision task that will identify the type of
m
.co
fruit and assign a label to it is called _________.
(A) Segmentation
e m
(B) Classification l as
ag
(C) Classification + Localization
(D) Object Detection

Ans (B)
OR
Classification

(1 Mark for the correct answer) m
m
c. o(ii) .co
em
Consider the following sentence : 1

e m s
la language ?
On seeing her son’s result, Pooja’s face turned red with anger.

las The word “red” demonstrates which characteristic of a gnatural
ag (A) Redundancy
(B) Context-dependent meaning
(C) Grammatical structure
(D) Temporal change

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 5/22]

e m
em as
s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl
Page 5 of 22

Ans (B)
OR
Context-dependent meaning

(1 Mark for the correct answer)

(iii) Ethical frameworks are primarily designed to : 1
(A) Increase the efficiency of AI algorithms.
(B) Ensure that choices made do not cause unintended harm.
(C) Reduce the cost of AI development.
(D) Speed up the AI project cycle.

Ans (B)
OR
Ensure that choices made do not cause unintended harm.

(1 Mark for the correct answer)

(iv) Statement 1 : Overfitting occurs when a model memorizes the training 1
data rather than learning patterns.
Statement 2 : Using the same data for training and evaluation helps the
model give accurate results.
(A) Both statements are correct.
(B) Both statements are incorrect.
(C) Statement 1 is correct but statement 2 is incorrect.
(D) Statement 1 is incorrect but statement 2 is correct.

Ans (C ) Statement 1 is correct but Statement 2 is incorrect.
OR
(A) Both statements are correct.
(As individual statements, both statement 1 and statement 2 are also
correct)

(1 Mark for the correct answer)

(v) Which learning approach would be most suitable for training an AI model 1
to park the car correctly ?
(A) Supervised Learning (B) Unsupervised Learning
(C) Transfer Learning (D) Reinforcement Learning

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 6/22]

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 6 of 22

.
.co s e m

s em Ans (D)
l a
a OR
Reinforcement Learning
ag
(1 Mark for the correct answer)

(vi) Which stage of the AI Project Cycle involves testing the model on newly 1
fetched data ?
(A) Data Exploration (B) Modelling
m
(C) Evaluation
om
(D) Deployment
. co
. c e m
Ans (C)
e m l as
OR
l as ag
ag
Evaluation

(1 Mark for the correct answer)

3. Answer any 5 out of the given 6 questions : 5X1=5

(i) In the context of autonomous vehicle safety systems, which type of 1
error would be most critical to minimize ?
(A) False Positive (detecting danger when there isn’t any)
m
(B) False Negative (failing to detect actual danger)
m .co
e
las
(C) True Positive (detecting danger correctly)
(D) True Negative (correctlygidentifying that there is no danger)
a
Ans (B)
OR
False Negative (failing to detect actual danger)

(1 Mark for the correct answer)

(ii) What is the range of possible pixel values in a byte image format ? 1
m
m (A) 0 to 100 (B) 0 to 255
.co
m .co (C) 1 to 256 (D) –128 to 127
s e m
s e g la
g la Ans (B)
a
a OR
0 to 255

(1 Mark for the correct answer)

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 7/22]

e m
em as
s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl
Page 7 of 22

(iii) An e-commerce platform analyzes customer purchase patterns to 1
recommend “Customers who bought product X also bought product Y.”
This uses :
(A) Classification model
(B) Regression model
(C) Association model
(D) Clustering model

Ans (C)
OR
Association model

(1 Mark for the correct answer)

(iv) As AI is essentially being used as a decision making / influencing tool, we 1
need to ensure that AI makes morally acceptable recommendations.
Which of the following is a key factor that can knowingly or unknowingly
influences our decision-making while designing an AI model ?
(A) Intuition and Values (B) Algorithm efficiency
(C) Data storage capacity (D) Processing speed

Ans (A)
OR
Intuition and Values

(1 Mark for the correct answer)

(v) Which NLP application helps in converting natural speech into text in real 1
time ?
(A) Keyword Extraction tool
(B) Translation of books from English to Hindi language
(C) Auto generated captions on YouTube
(D) Classifying raw text into pre-defined groups

Ans (C)
OR
Auto generated captions on YouTube

(1 Mark for the correct answer)

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 8/22]

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 8 of 22

.
.co s e m

s em (vi) In supervised learning, what is the purpose of the testing dataset ?
l a 1
a (A) To train the model. ag
(B) To evaluate the model’s accuracy.
(C) To create new features.
(D) To label the data.

Ans (B)
OR
m
om
To evaluate the model’s accuracy.
. co
. c e m
m
(1 Mark for the correct answer)
e a s
l5 x 1 = 5
4.
l a s
Answer any 5 out of the given 6 questions : ag
(i)
g
aIn a fire alarm system, if the model predicts “Fire Present” when there is 1
actually no fire, this is classified as :
(A) True Positive (TP) (B) True Negative (TN)
(C) False Positive (FP) (D) False Negative (FN)

Ans (C)
m
.co
OR
False Positive (FP)
e m
(1 Mark for the correct answer)
l as
(ii) g example of a Value-based Framework for AI.
Assertion (A): Bioethics isaan 1
Reason (R) : Bioethics deals with ethical issues related to health,
medicine, and biological sciences.
(A) Both (A) and (R) are true and (R) is the correct explanation of (A).
(B) Both (A) and (R) are true,but (R) is not the correct explanation of (A).
(C) (A) is true, but (R) is false.
m
m (D) (A) is false, but (R) is true.
.co
m .co s e m
s e Ans (D)
g la
la a
OR

ag (A) is false, but (R) is true.

(1 Mark for the correct answer)

(iii) Which scenario best represents a regression problem ? 1
(A) Identifying whether an email is spam.

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 9/22]

e m
em as
gl
​

s
​

​

​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 9 of 22

(B) Grouping customers by behaviour.
(C) Predicting tomorrow’s temperature.
(D) Recognizing faces in photos.

Ans (C)
OR
Predicting tomorrow’s temperature.

(1 Mark for the correct answer)

(iv) Which of the following best describes the relationship between pixels 1
and image resolution ?
(A) More pixels result in lower image quality.
(B) Pixels and resolution are unrelated concepts.
(C) Resolution depends only on image file size.
(D) The number of pixels in an image is known as resolution.

Ans (D)
OR
The number of pixels in an image is known as resolution.

(1 Mark for the correct answer)

(v) Precision is defined as : 1
(A) The ratio of correctly predicted positive observations to total
observations.
(B) The ratio of correctly predicted positive observations to total
predicted positive observations.
(C) The ratio of correctly predicted negative observations to total
observations.
(D) The harmonic mean of true positives and true negatives.

Ans (B)
OR
The ratio of correctly predicted positive observations to total predicted
positive observations.

(1 Mark for the correct answer)

(vi) Which type of chat bot requires coding and works on bigger databases 1
directly ?

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 10/22]
​
​

​

​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 10 of 22

.
.co s e m

s em (A) Script bot
l a
a (B) Smart bot ag
(C) Traditional bot
(D) Rule-based bot

Ans (B)
OR
Smart bot
m
om
(1 Mark for the correct answer) . co
. c e m
m 5sx 1=5
5.
s e
Answer any 5 out of the given 6 questions :
g l a
(i)
g a
l AI domain would be most suitable for developing a price
Which a 1
acomparison website ?
(A) Computer Vision
(B) Natural Language Processing
(C) Statistical Data
(D) Robotics

m
.co
Ans (C)
OR
e m
Statistical Data
l as
ag
(1 Mark for the correct answer)

(ii) Assertion (A): Converting text to lowercase is preferable in text 1
preprocessing.
Reason (R) : It ensures that “Hello” and “hello” are treated as the same
word by the machine.
(A) Both (A) and (R) are true and (R) is the correct explanation of (A).
m
m (B) Both (A) and (R) are true,but (R) is not the correct explanation of (A).
.co
m .co (C) (A) is true, but (R) is false.
s e m
s e (D) (A) is false, but (R) is true.
g la
g la a
a Ans (A)
OR
Both (A) and (R) are true and (R) is the correct explanation of (A).

(1 Mark for the correct answer)

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 11/22]

e m
em as
s gl
​
​

​

​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 11 of 22

(iii) In the context of Computer Vision vs Image Processing, which statement 1
correctly differentiates them ?
(A) Computer Vision and Image Processing are exactly the same.
(B) Computer Vision enhances the image while Image Processing does not.
(C) Computer Vision is a superset of Image Processing.
(D) Image Processing is a superset of Computer Vision.

Ans (C)
OR
Computer Vision is a superset of Image Processing.

(1 Mark for the correct answer)

(iv) State True or False : 1
In machine learning, the error is used to see how accurately the model
can predict data.

Ans True/T

(1 Mark for the correct answer)

(v) A company wants to analyze customer reviews to understand satisfaction 1
levels. Which NLP application would be most suitable ?
(A) Text classification
(B) Sentiment analysis
(C) Keyword extraction
(D) Language translation

Ans (B)
OR
Sentiment analysis

(1 Mark for the correct answer)

(vi) An AI model was tested with 1000 test samples. If True Positive (TP)= 200, 1
True Negative (TN) = 600, False Positive (FP) = 100, False Negative (FN) =
100, how many total predictions were correct ?
(A) 300 (B) 600
(C) 800 (D) 900

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 12/22]

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 12 of 22

.
.co s e m

s em Ans (C)
l a
a OR
800
ag
(1 Mark for the correct answer)

SECTION - B
(Subjective Type Questions)

m
co
Answer any 3 out of the given 5 questions on Employability Skills in 20–30 words
each.
. c om 3x2=6
e m .
e m a2s
6.
s
Write the 7 C’s of communication.
a g l
7g l of communication: a
Ans
a ● Clear
C’s

● Concise
● Concrete
● Correct
● Coherent
● Complete
● Courteous

m
.co
(2 Marks for all 7 C’s )
OR
(1½ Marks for any 5-6 C’s)
e m
OR
l as
(1 Mark for any 3-4 C’s)
OR ag
(½ Mark for any 1-2 C’s)

7 (a) What is emotional intelligence ? 1

Ans Emotional intelligence is the ability to identify and manage one’s own
emotions, as well as the emotions of others.
OR
o m
m . c
. co Itrelationships, e m
involves using emotional data to guide thinking, behavior, and
s
s em aiming for improved self-awareness,
a
empathy,
g l
and

la
conflict resolution.
g OR a
a
It comprises five key components: self-awareness, self-regulation,
motivation, empathy, and social skills.

(1 mark for any correct answer)

m . c
c. o
​

​

​

​

​

​

​

​

​

​

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 13/22]

m
​
​
​

e
​
​
​
​

em as
s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl
Page 13 of 22

7 (b) Name any two skills included in emotional intelligence. 1

Ans ● Emotional awareness
● Managing emotions
● Harnessing emotions

(½ mark each for any 2 correct skills)

8. How ICT skills help us in our day-to-day activities ? 2

Ans ● ICT (Information and Communication Technology) skills help us to
communicate, run our business and stay connected with our
family and friends.
● ICT skills (Information and Communication Technology) enhance
daily life by enabling instant communication, efficient
information access, and streamlined task management.
● ICT (Information and Communication Technology) skills facilitate
online shopping, digital banking, remote work, and
entertainment.
● ICT (Information and Communication Technology) skills help in
improving education through e-learning and enhancing healthcare
via Telemedicine.

(2 marks for any two correct / relevant activities)
OR
(1 mark for any one correct / relevant activity)

9. State the qualities to become a successful entrepreneur. 2

Ans ● Confident
● Keep trying new idea
● Patience
● Creative
● Responsible
● Decision making
● Hard working
● Problem solving
● Risk Taking
● Do not give up

(2 marks for any two correct / relevant answer)
OR
(1 mark for any one correct / relevant answer)
​
​
​
​

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 14/22]
​
​
​
​
​
​
​
​
​
​
​
​


​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 14 of 22

.
.co s e m

s em 10. Define the term ‘Sustainable Development’.
l a 2
a Ans ag satisfies the needs of
Sustainable Development is the development that
the present without compromising the capacity of future generations,
guaranteeing the balance between economic growth, care for the
environment and social well-being.
OR
Development that meets current needs without destroying resources for
the future.
OR
m
co
Sustainable Development protects the environment from degradation

. c om
like pollution , deforestation and resource depletion.
e m .
(2 marksm
e for any correct / relevant answer) l as
l as ag
g
a 4 out of the given 6 questions in 20-30 words each.
Answer any 4 x2 = 8

11. Explain the difference between sector-based and value-based ethical 2
frameworks with one example of each.

Ans Sector-based ethical Frameworks (Any one):
● These are frameworks tailored to specific sectors or industries.
● Different sectors face different ethical challenges.
m
.co
● Sector-based ethical frameworks may also apply to domains such
as finance, education, transportation, agriculture, governance,
and law enforcement. e m
l as
Example : Bioethics (focusesgon ethical considerations in healthcare,
a
patient privacy, data security).

Value-based ethical Frameworks (Any one):
● Value-based frameworks focus on fundamental ethical principles
and values guiding decision making.
● It reflects the different moral philosophies that inform ethical
reasoning.
● Value-based frameworks are concerned with assessing the moral
m
.co
worth of actions and guiding ethical behaviour.
m Example : Rights-based framework (valuing human life over other
m .co s e m
s e considerations), Virtue-Based(Whether developers
l
uphold a
ethical values),

g l a Utility-Based(Maximize overall good).
ag
a (1 mark for any one difference and ½ mark for each example)

12. Give any two characteristics of a Classification Model. 2

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 15/22]

e m
​

s
​
​

em gl a
​
​

s
​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 15 of 22

Ans Characteristics of a Classification Model (any two):
● It is a type of Supervised Learning model.
● The data is classified according to the labels.
● The model works on a discrete data set which means the data
need not be continuous.

Example: In the grading system, students are classified on the basis of
the grades they obtain with respect to their marks in the examination.

(1 mark each for any correct / relevant Characteristic )

13. How do computers store RGB images ? 2

Ans ● All the colored images are made up of three primary colors Red,
Green, and Blue. These colors can be made by combining different
intensities of red, green, and blue.
● Every RGB image is stored in the form of three different channels
called the R Channel, G Channel, and B Channel.
● Each plane separately has many pixels with each value varying
from 0-255.
● This means that in an RGB image, each pixel has a set of three
different values which together give color to that particular pixel.

(2 marks for any correct / relevant answer)

14. Give two differences between Supervised and Unsupervised learning. 2

Ans

Supervised Learning Unsupervised Learning

Uses labelled data. Uses un-labelled data.

Predicts accurate outcomes or Discovers hidden patterns,
classifies data based on known structures, or groupings on
labels. unknown data.

Less complex, as the model learns More complex as unsorted and
from labelled data with clear messy data is used for input.
guidance.

User supervision/intervention is No user supervision/intervention
required. is required.

Types : Classification or Regression. Types : Clustering, Association,
Anomaly Detection,
Dimensionality Reduction.
​
​
​

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 16/22]
​
​
​
​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 16 of 22

.
.co s e m

s em l a
ag
Example- Spam Email,Fraud Example- Customer
a Detection, Predicting house prices. Segmentation, Identifying
products often brought together,
Grouping shopping behaviour.

(1 mark for each correct difference (Any two))
(½ mark each for any correct example, if only example is given)

15. Explain Train-test split technique with respect to machine learning 2
m
algorithm.
om . co
. c e m
Ans m
Train-test split :
e l as
l as
● The train-test split is a technique for evaluating the performance
ag
ag of a machine learning algorithm.
● It can be used for any supervised learning model.
● The procedure involves taking a dataset and dividing it into two
subsets:
○ The training dataset : Used to make the model learn.
○ The testing dataset : Used to evaluate the model’s
performance on new, unseen data.
● The train-test procedure is appropriate when there is a sufficiently
large dataset available.
m
● The ratio of training and testing dataset should be 80-20% or 70-30
%.
m .co
● The objective is to estimate the performance of the machine
s e
a
learning model on new data: data not used to train the model.
l
ag
(2 marks for any correct/relevant answer )

16. How is Stemming different from Lemmatization ? Explain how the word 2
“Wolves” would be processed by stemming and lemmatization.

Ans
Stemming Lemmatization
m
m It is the process in which the It is the process in which the
.co
m .co affixes of words are removed and
the words are converted to their
affixes of words are removed and
s e
the words are converted to their
m
s e base form.The resultant stem
g la
base form.The resultant Lemma

g la word may/may not be meaningful. a
word is always meaningful.
a Stemming takes less time than It takes longer time to execute
lemmatization. than stemming

Input Word : Wolves

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 17/22]
​

m
​
​

e
​
​
​

s
​

em
​

s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl a
Page 17 of 22

Stemming Output : Wolv (may not be meaningful)

Lemmatization Output : Wolf (meaningful word)

(1 mark for correct difference (any one))
(½ mark for correct Stem word)
(½ mark for correct Lemma word)

Answer any 3 out of the given 5 questions in 50– 80 words each 3 x 4 = 12

17. Differentiate between Deep Learning, Artificial Intelligence and 4
Machine Learning. Also draw a labelled Venn diagram depicting the
relationship between AI, ML and DL.

Ans Artificial Intelligence or AI for short, refers to any technique that
enables computers to mimic human intelligence. An artificially
intelligent machine works on algorithms and data fed to it and gives
the desired output.
Example of AI:
● A chess-playing system like Deep Blue (IBM’s system that
defeated Garry Kasparov)
● Virtual assistants like Siri
● Rule-based expert systems in medical diagnosis

Machine Learning, or ML for short, enables machines to improve at
tasks with experience. The machine here learns from the new data
fed to it while testing and uses it for the next iteration. It also takes
into account the times when it went wrong and considers the
exceptions.
Example of ML:
● Email spam detection
● Movie recommendations like those used by Netflix
● Fraud detection systems

Deep Learning or DL for short, enables software to train itself to
perform tasks with vast amounts of data. Since the system has got
huge set of data, it is able to train itself with the help of multiple
machine learning algorithms working together to perform a specific
task.
Example of DL:
● Image recognition in self-driving cars
● Face recognition systems
● Language models like ChatGPT

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 18/22]
​
​
​
​
​
​

​

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 18 of 22
​
​
​

.
.co s e m

s em l a
ag
Artificial Intelligence is the umbrella term which holds both Deep
a Learning as well as Machine Learning.
Deep Learning, on the other hand, is the very specific learning
approach which is a subset of Machine Learning as it comprises of
multiple Machine Learning algorithms.

m
om . co
. c e m
e m l as
l as ag
ag

(1 mark for each correct answer / difference)
(1 mark for correct venn diagram)

18. Consider the following scenarios and identify which AI domain would 4

m
.co
be most appropriate for each, with justification :

e m
Ans (A)
s
An AI based education platform needs to translate to English
l a
language and analyze thousands of student essays to provide instant
ag
feedback on grammar, content quality and writing style.

AI Domain : Natural Language Processing (NLP)
Justification : Essay translation involves change of language and
analysis involves understanding text, grammar checking, and content
evaluation, which are core NLP applications.
(1 mark for correct identification of AI domain)
(1 mark for correct / relevant justification)
m
m
Ans (B) An AI based application installed on a busy crossing in a metropolitan
.co
m .co city scans all vehicles driving through that crossing during peak
s e m
la
traffic hours and categorizes them into four wheelers and two
s e wheelers.
g
g la a
a AI Domain : Computer Vision
Justification : The system analyzes visual data (images/videos from
cameras) to identify and classify vehicles. Since it processes and
interprets images, it falls under Computer Vision.
(1 mark for correct identification of AI domain)
(1 mark for correct / relevant justification)

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 19/22]

e m
em as
s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl
Page 19 of 22

19. Read the following paragraph and answer the questions that follow :
PQR Security Solutions has designed an AI Model to detect cyber
attacks on E-Commerce websites. For this, various network activities
were monitored and analyzed on one of the websites. The model was
tested on a dataset of 1500 network activities. Out of these, the
model correctly predicted that 1000 were cyber attacks. It also
correctly identified that 250 were not cyber attacks. However, the
model predicted that 200 were cyber attacks but actually they were
not. Additionally, it predicted that 50 were not cyber attacks but
they actually were.

(A) Draw the confusion matrix based on the given scenario. 2

Ans (A)
REALITY
CONFUSION MATRIX
YES NO
YES 1000(TP) 200 (FP)
PREDICTION
NO 50 (FN) 250(TN)

OR

PREDICTION
CONFUSION MATRIX
YES NO
YES 1000(TP) 50 (FN)
REALITY
NO 200 (FP) 250(TN)

(2 marks for drawing confusion matrix with all correct values at
correct positions)

OR
(1 ½ mark for drawing confusion matrix with any 2 correct
values at correct positions)

OR
(½ mark for drawing confusion matrix without/incorrect values)

Ans (B) How many total cases are True Negative in the above scenario ? 1

True Negative (TN) : 250

(1 mark for the correct answer)

Ans (C) Calculate Precision. 1

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 20/22]

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 20 of 22

.
.co s e m

s em TP = 1000, TN = 250, FP = 200, FN = 50
l a
a Precision = TP/(TP + FP)
= 1000/1200
ag
= 0.833
= 83.3 %

(1 mark for the correct answer)
OR
(½ mark for writing correct formula but incorrect posting of
values )
m
om . co
OR
. c e m
(½ mark for writing formula only)
e m l as
a s NOTE- Mathematical calculations can be ignored
g
a 3
20. (A)glExpand and define the terms CNN and ANN.
a
Ans (A) Convolutional Neural Network (CNN) – Convolutional Neural Network
is a Deep learning algorithm which can take in an input image, assign
importance (learnable weights and biases) to various aspects/objects
in the image and be able to differentiate one from the other. CNN is
specially designed to process images by automatically extracting
visual features.

m
Artificial Neural Network (ANN) – Artificial Neural networks are
.co
modelled on the human brain and nervous system. They are able to
m
e
automatically extract features without input from the programmer.
s
a
Every neural network node is essentially a machine learning
l
ag
algorithm. It is useful when solving problems for which the data set is
very large.

(½ mark each for the correct full form)
(1 mark each for the correct definition / explanation / relevant
answer )

(B) In the diagram of neural network given below, identify the layer that 1
should be depicted in Box 1 and Box 2 :
m
m .co
m .co s e m
s e g la
g la a
a

m . c
c. o
[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 21/22]

e m
em as
s
For more Question Papers, Sample Papers, Notes & Syllabus visit
gl
Page 21 of 22

Ans (b) Box 1 : Input Layer
Box 2 : Hidden Layer

(½ mark each for the correct answer. No marks to be awarded
for naming Box 3)

21. Consider the following documents : 4

Document 1 : Data Science requires information.
Document 2 : Information analysis requires data.

Implement all the four steps of Bag of Words (BoW) model to create a
document vector table.

Ans Step 1 : Text Processing (Preprocessing), after normalization :
Document 1 : [data, science, requires, information]
Document 2 : [information, analysis, requires, data]

Step 2 : Create Dictionary (Vocabulary)
Unique words :data, science, information, analysis, requires

Step 3 : Create Document Vector
Count frequency of each vocabulary word in Document 1

data science requires information analysis

Doc 1 1 1 1 1 0

Step 4 : Create Document Vector table for all documents

data science requires information analysis

Doc 1 1 1 1 1 0

Doc 2 1 0 1 1 1

(1 mark for each correct step)
(No mark to be deducted for combining Step 3 and Step 4)

[ CBSE MS ARTIFICIAL INTELLIGENCE SUBJECT CODE 417 PAPER CODE 104/SET4 CLASS 10 MAIN 2026 PAGE 22/22]

For more Question Papers, Sample Papers, Notes & Syllabus visit Page 22 of 22