Pre-Board Exam (2024-25)

Class: X
Subject: Artificial Intelligence (417)

Time: 2 hours Max Marks: 50

MARKING SCHEME

SECTION A: OBJECTIVE TYPE QUESTIONS

Q.
Answer Marks
No.
Q. 1

i. b) External Motivation 1

ii. a) Selected 1
d) A is not correct but R is correct
iii. 1
c) Both of the above
iv. 1

v. c) Cultural barriers 1

vi. (d) Reduced inequalities 1

Q. 2
(a) Both A and R are correct and R is the correct explanation of A
i. 1

ii. (b) Data Privacy 1

iii. (c) Both Statement1 is incorrect and Statement2 are correct 1

iv. Larger 1

v. (c) csv 1

vi. (a) stop word 1

Q. 3
i. (b) I, ii and iv 1
 ii. (d) System hacking 1

iii. (d) All of the above 1

(b) To understand visual information
iv. 1

v. (b) Smart Bot 1

vi. (b) Precision and Recall 1

Q. 4
i. (C) Deep Learning 1
(c) Statement1 is correct but Statement2 is incorrect
ii. 1
(b) high precision high recall
iii. 1

(c) Classification and localization

iv. 1

v. (b) Sentiment Analysis 1

vi. Overfitting 1
Q. 5
i. (b) Natural Language Processing 1

ii. Recall 1
(a) Categorizing each pixel in the image in to a specific class
iii. 1
(c) Automatic summarization
iv. 1

v. (c) Silvi 1
(b) confusion matrix
vi. 1
 SECTION B: SUBJECTIVE TYPE QUESTIONS

Answer any 3 out of the given 5 questions on Employability Skills (2 x 3 = 6 marks)

Answer each question in 20 – 30 words.

Mark
s
Q.
QUESTION
No.

Q. 6 1. Not understanding language 2

2. Cultural difference
3. Communication problem etc
(2 marks for any two correct points from the above)
Q. 7 Specific, Measurable, Achievable, Relevant, and Time-Bound 2
(1 mark for expansion only 2 for explanation)
Q. 8 2
1) Never eat anything over a keyboard. As crumbs of food can damage the
internal part of a keyboard.
2) Always clean a Keyword with a soft brush to remove crumbs and dust
particles.
3) Wipe the screen with a soft cloth to remove any finger marks.
4) 4) Avoid eating and keeping glasses of water near s computer as liquid split over
an electronic device can spoil it beyond repair.
5) (2 marks for any two correct points from the above)
Q. 9 1. Entrepreneurs are high risk takers. They are neither high nor low risk – takers. 2
2. They always prefer situations which lead to generating profits.
3. Entrepreneurs become rich as they start a new business.
4. Entrepreneurs have limited dedication which is the key to success.
(2 marks for any two valid points)
Q. 10 Any two real life examples. 2
(2 marks for any two correct points)
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)

Q. 11 1. If it is not relevant and authentic then the testing data may go wrong or produced 2
irrelevant predictions.
2. It increases the AI Project efficiency.
(2 marks for any one correct point with explanation)

Q. 12 1. supervised learning uses labeled input and output data 2

2. supervised learning models tend to be more accurate than unsupervised
learning models
3. Supervised learning is a simple method for machine learning.
(2 marks for any two correct advantages)
 Q. 13 There could be many ways and sources from where we can collect structures and 2
reliable datasets namely Surveys, Web scrapping, Sensors, Cameras,
Observations, Research, Investigation, API etc.
(1 mark for each source name )

Q. 14 An RGB image refers to an image that stores data for red, green, and blue color channels. 2
These images can be stored in a single file or in multiple files, with each file representing
a different wavelength.
(1 mark for explanation; 1 mark for example)
Q. 15 Bag of Words is a NLP model which helps in extracting features from textual data. It 2
converts text sentences into numeric vectors by returning the unique words along with its
number of occurrences.
“Stop words” are the most common words in a language like “the”, “a”, “on”, “is”, “all”.
These words do not carry important meaning and are usually removed from texts.
(1 mark for each correct explanation)
Q. 16 2
Reality
Confusion Matrix Yes No

Yes 55 10
Prediction
No 15 20

(½ marks each for mapping the values in the correct section, ½ *4=2 marks)

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)
Q. 17 1 mark for AI definition 4
1 mark for correct AI real life application
2 marks for the ways AI machine is trained – supervised, unsupervised with explanation
Q. 18 The 4Ws Problem canvas helps in identifying the key elements related to the problem. The 4
4Ws are Who, What, Where and Why
● The “Who” block helps in analysing thepeople getting affected directly or
indirectly due to the problem.
● The “What” block helps us to determine the nature of the problem.
● The “Where” block helps us to look into the situation in which the problem arises,
the context of it, and the locations where it is prominent.
● The “Why” block suggests to us the benefits which the stakeholders would get
from the solution and how it will benefit them as well as the society

Our [stakeholders] Who

Have a [need] What
problem that
When/while [contex Where
t/
location
 Problem Statement Template /
situatio
n]
An ideal [solution] Why
solution
would be

(½ mark each for explanation of 4w s; 2 marks for drawing the problem statement
template with correct words in it or explaining the problem statement template)
or
(1 mark to be allotted if only 4Ws are written without explanation)
Q. 19 Figure 1 Supervised learning 4
In a supervised learning model, the dataset which is fed to the machine is labelled. In
other words, we can say that the dataset is known to the person who is training the
machine only then he/she is able to label the data. A label is some information which can
beused as a tag for data.

Figure 2 Unsupervised learning

An unsupervised learning model works on unlabeled dataset. This means that the data
which is fed to the machine is random and there is a possibility that the person who is
training the model does not have any information regarding it. The unsupervised
learning models are used to identify relationships, patterns and trends out of the data
which is fed into it. It helps the user in understanding what the data is about and what are
the major features identified by the machine in it.

(1 mark each for identifying each term supervised learning and unsupervised learning; 1
mark per explanation of each term)
Q. 20 Normalization of the given text: 4
1) Sentence Segmentation:
1. Raj and Vijay are best friends.
2. They play together with other friends.
3. Raj likes to play football but Vijay prefers to play online games.
4. Raj wants to be a footballer.
5. Vijay wants to become an online gamer.

2) Tokenization:
 3) Removing Stop words, Special Characters and Numbers:
In this step, the tokens which are not necessary are removed from the token list. So, the
words and, are, to, an, (Punctuation) will be removed. Converting text to a common
case:

4) Convert the whole text into a similar case

After the stop words removal, we convert the whole text into a similar case, preferably
lower case. Here we don’t have words in different case so this step is not required for
given text.

5) Stemming/ Lemmatization:
In this step, the remaining words are reduced to their root words. In other words,
stemming is the process in which the affixes of words are removed and the words are
converted to their base form. Word Affixes Stem
Likes -s Like
Prefers -s Prefer
Wants -s want
In the given text Lemmatization is not required.
Lemmatization: Lemmatization is the process in which the affixes of words are
removed and the words are converted to their base form with meaning.
Lemmatization makes sure that lemma is a word with meaning.

Finally, we reduced Given Text (Corpus) into Normalized Text.

1. raj, vijay, best, friends
2. play, together, with, other, friends
3. raj, like, play, football, but, vijay, prefer, play, online, games
4. raj, want, be, footballer
5. vijay, want, become, online, gamer
Q. 21 Ans: (i)the total number of wrong predictions made by the model is the sum of false 4
positive and false negative. FP+FN=25+15= 40

(ii) Precision=TP/(TP+FP)

=55/(55+25) =50/80

=0.625

Recall=TP/(TP+FN)

=55/(55+15)

=50/70

=0.71

F1 Score = 2*Precision*Recall/(Precision+Recall)

=2*0.625*0.71/(0.625+0.71)

=0.8875/1.335

=0.67

(1 marks for part (i) and ½ mark for each formula and ½ mark each for substitution of
values in part(ii))

Please note: the mathematical calculations can be ignored