THE HINDU SENIOR SECONDARY SCHOOL, INDIRANAGAR

REVISION 1 (2024 – 2025) DATE:

CLASS: 10 ARTIFICIAL INTELLIGENCE MARKS: 80 TIME: 3hr.

General Instructions:
i) This question paper consists of questions in two sections: Section A & Section B.
ii) Section A has objective type questions whereas Section B contains subjective type
questions.
iii) Section A – Objective type questions (40 marks).
a) This section has 06 questions.
b) Marks allotted are mentioned against each question/part.
c) There is no negative marking.
d) Do as per the instructions given.
iv) Section B – Subjective type questions (40 marks).
a) Marks allotted are mentioned against each question/part.
b) Do as per the instructions given.
Section – A
Objective Type Questions
Q. 1 Answer the following questions. (7 X 1 = 7)
i) (c) Natural Language Processing
ii) c) Labelling individual instances of objects
iii) (b) Rare word
iv) Resolution
v) Syntax: Syntax refers to the grammatical structure of a sentence.
Semantics: It refers to the meaning of the sentence.
vi) c. False Negatives
vii) Prediction and Reality are the two parameters considered for Evaluation of a
model
Q. 2 Answer the following questions. (6 X 1 = 6)
i) False
ii) (c) Bag of words
iii) Pooling
iv) Natural Language Toolkit (NLTK)
v) a) Apply different effects to an image
vi) False Negative
Q. 3 Answer the following questions. (7 X 1 = 7)
i) (b) Grammatical structure of a sentence
ii) F1 score
iii) d) Automatic Summarisation
iv) c) Instance Segmentation
v) Natural Language Processing (NLP)
vi) Prediction
vii) b) Both Statement 1 and Statement 2 are incorrect
Q. 4 Answer the following questions. (7 X 1 = 7)
i) Three channels
ii) b) Relevant and Authentic Training Data
iii) (a) care
iv) (c) Recall
v) (b) Computer Vision
vi) b) Both Statement 1 and Statement 2 are incorrect.
vii) a) 12
Q. 5 Answer the following questions. (6 X 1 = 6)
i) (b) When a spam email is mistakenly identified as legitimate.
ii) Kernel
iii) (a) Both Statement 1 and Statement 2 are correct.
iv) (c) Natural Language Processing (NLP)
v) Overfitting
vi) Pixels
Q. 6 Answer the following questions. (7 X 1 = 7)
i) Accuracy
ii) a) Rare / valuable words
iii) b) ii and iii
iv) True
v) d) Text and speech
vi) True
vii) Automatic Text Summarization, Sentiment Analysis, Text classification,
Virtual Assisstants, Writing Enhancement and Grammar checkers, Large
Language Modals, Chatbots, Search Engines, Language Translator.
(Any 2)
(1/2 mark for each correct answer)

Section – B
Subjective Type Questions
Answer the following questions in 20 – 30 words each. (12 X 2 = 24)
Q. 7 Models that use the training dataset during testing, will always results
in correct output. This is known as overfitting.
Q. 8 Four basic Computer Vision tasks are
(i) Image classification – It predicts the class of an object in an image.
(ii) Image Localisation – It locates the presence of objects in an image
and indicate them with bounding boxes
(iii) Object Detection – It locates the presence of objects with a
bounding box and classes of the located objects in an image.
(iv) Image Segmentation – A segmentation returns much more detailed
information about the image.
Q. 9 Term frequency–inverse document frequency, is a numerical statistic
that is intended to reflect how important a word is to a document in a
collection or corpus. (1 mark)
The number of times a word appears in a document divided by the
total number of words in the document. Every document has its own
term frequency. ( ½ mark )

Some of its applications are:

• Document Classification
• Topic Modelling
• Information Retrieval System
• Stop word filtering
(any 2)( ½ mark each)
Q. 10

(½ marks each for mapping the values in the correct section, ½ *4=2
marks)
Q. 11 Here, the red dashed line is model’s output while the blue crosses are
actual data samples.
● The model’s output does not match the true function at all. Hence
the model is said to be under fitting and its accuracy is lower.
● In the second case, model performance is trying to cover all the data
samples even if they are out of alignment to the true function. This
model is said to be over fitting and this too has a lower accuracy.
● In the third one, the model’s performance matches well with the true
function which states that the model has optimum accuracy and the
model is called a perfect fit.
Q. 12 False Positive: Mail is predicted as “spam” but it is “not spam”.
False Negative: Mail is predicted as “not spam” but it is “spam”.
Of course, too many False Negatives will make the spam filter
ineffective but False Positives may cause important mails to be missed
and hence Precision is not usable.
Q. 13
Script Bots Smart Bots
They are easy to build and simple They take more time and effort
in their functionality to build. They are flexible and
powerful. They learn and
improve with experience.
They use pre-written scripts to They use large databases and
interact with users. resources to generate responses
independently.
They are often free and easy to These are more complex to
integrate into a messaging implement and may involve a
platform. higher cost.
They do not require advanced They need coding skills.
language processing skills.
They have limited functionality. They have a wide range of
functions and capabilities.
They are used for simple Virtual assistants, like Siri,
functions, like answering Google Assistant, Alexa, fall
frequently asked questions, under the category of Smart
setting appointments, connecting bots. They understand and
them to human executives once respond to a variety of user
they are unable to handle the queries and perform various
conversation, and on messaging tasks, answer questions, and
apps to give predefined control smart devices in response
responses. to natural language.
Q. 14 A pixel, short for "picture element," is the smallest unit of a digital
image, Resolution of an image refers to the number of pixels in an
image, across the width and height. The arrangement and colour
values of pixels determine an image's resolution, quality, and overall
visual clarity.
Q. 15 Stopwords in the given sentence which should not be removed are:
@, . (fullstop) ,_(underscore) , 123(numbers)
These tokens are generally considered as stopwords, but in the above
sentence, these tokens are part of email id. removing these tokens may
lead to invalid website address and email ID.
So these words should not be removed from the above sentence.
(1 mark for identifying any two stop words from the above, and 1 mark
for the valid justification.)
Q. 16 Some common applications of computer vision are,
a) Facial Recognition
b) Face Filters
c) Image search on search engines
d) Computer Vision in Retail
e) Inventory Management
f) Self – Driving Cars
g) Google Lens / Translate App
h) Medical imaging
i) Livestock Farming
j) Agriculture
Q. 17 Importance of Evaluation:
Evaluation is a process that critically examines a program. It involves
collecting and analyzing information about a program's activities,
characteristics, and outcomes. Its purpose is to make judgments about
a program, to improve its effectiveness, and/or to inform programming
decisions.
• Evaluation is important to ensure that the model is operating
correctly and optimally.
• Evaluation is an initiative to understand how well it achieves its
goals.
• Evaluations help to determine what works well and what could be
improved in a program
Q. 18 Tokenization is a term that describes breaking a document or body of
text into small units called tokens. Tokens is a term used for any word
or number or special character occurring in a sentence. Doing so makes
it easier for a machine to process the text.
The given sentence contains 15 tokens.
Answer the following questions in 50 – 80 words each. (4 X 4 = 16)
Q. 19 Yes, we might face any challenges if we try to teach computers how to
understand and interact in human languages.
The possible difficulties are:
1. Arrangement of the words and meaning - the computer has to
identify the different parts of a speech. Also, it may be extremely
difficult for a computer to understand the meaning behind the
language we use.
2. Multiple Meanings of a word - same word can be used in a number
of different ways which according to the context of the statement
changes its meaning completely.
 3. Perfect Syntax, no Meaning - Sometimes, a statement can have a
perfectly correct syntax but it does not mean anything.
For example, take a look at this statement:
Chickens feed extravagantly while the moon drinks tea. This statement
is correct grammatically but does this make any sense?
In Human language, a perfect balance of syntax and semantics is
important for better understanding.
(1 mark for Yes and 1 mark each for the points on possible difficulties)
Q. 20 Normalization of the given text:
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.

Raj and Vijay are best friends .

They play Together with other friends .
5. Vijay wants to become an online gamer.
Tokenization:

Same will be done for all sentences.

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:
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. Stemming:
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.

Given Text:
Raj and Vijay are best friends. They play together with other friends.
Raj likes to play football but Vijay prefers to play online games. Raj
wants to be a footballer. Vijay wants to become an online gamer.
Normalized Text
Raj and Vijay best friends They play together with other friends Raj
likes to play football but Vijay prefers to play online games Raj wants
to be a footballer Vijay wants to become an online game
Q. 21 CNN (Convolutional Neural Network):
CNN is a type of deep learning algorithm primarily used for tasks
involving image and video recognition, classification, and analysis. It is
designed to automatically and adaptively learn spatial hierarchies of
features from input images, making it highly effective for visual data
processing.
Architecture of a CNN:

A typical CNN consists of the following layers:

1. Convolutional Layer:
o This is the core building block of a CNN.
o It applies convolution operations to extract features such
as edges, textures, and patterns from the input image.
o The output of this layer is called a feature map.
2. Activation Function (e.g., ReLU):
o An activation function like ReLU (Rectified Linear Unit) is
applied to introduce non-linearity into the network.
o It ensures the CNN can learn complex patterns.
3. Pooling Layer (e.g., Max Pooling):
o Reduces the spatial dimensions of feature maps,
decreasing the computational load and preserving
important features.
o It also helps make the network invariant to small
translations or distortions in the input.
4. Fully Connected Layer (Dense Layer):
o After feature extraction, the fully connected layer
interprets the features and maps them to class scores for
classification tasks.
5. Output Layer:
o Often uses a softmax or sigmoid function for multi-class
or binary classification, respectively.

Overall Workflow:

• Input image → Convolution → Activation → Pooling → Fully

Connected → Output

This pipeline enables CNNs to identify hierarchical and spatial features

efficiently.
Q. 22 Accuracy
Accuracy is defined as the percentage of correct predictions out of all
the observations

= (75+15) / (75+15+5+5)
= (90 / 100)
=0.9
Precision
Precision is defined as the percentage of true positive cases versus all
the cases where the prediction is true.

= 75 / (75+5)
= 75 /80
= 0.9375
Recall
It is defined as the fraction of positive cases that are correctly
identified.

= 75 / (75+5)
= 75 /80
= 0.9375
F1 Score
F1 score is defined as the measure of balance between precision and
recall.

Therefore,
= 2 * (0.8789 / 1.875)
= 2 * 0.46875
= 0.9375
Accuracy= 0.9%
Precision=0.9375%
Recall=0.9375
F1 Score=0.9375.
Here precision, recall, accuracy, f1 score all are same