PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 1

Artificial intelligence : PART B--Unit–2: ADVANCED CONCEPTS OF MODELING IN AI

MCQ:
1. 1. In which type of machine learning is the data labeled with the desired output? a)
Supervised Learning b) Unsupervised Learning c)
Reinforcement Learning d) Deep Learning
ANS: a) Supervised Learning

2. An email spam filter that learns to identify spam emails based on labeled examples is an
application of:
a) Supervised Learning b) Unsupervised Learning c)
Reinforcement Learning d) Transfer Learning
ANS: a) Supervised Learning

3. A machine learning algorithm that groups similar customer purchases into clusters for
recommendation systems uses:
a) Supervised Learning
b) Unsupervised Learning
c) Reinforcement Learning
d) Neural Networks
ANS: b) Unsupervised Learning
4. What is the primary goal of machine learning?
(a) To enable computers to learn from data and improve performance
(b) To enable computers to store data only
(c) To enable computers to do every task automatically
(d) To enable computers to create objects
Answer: (a) To enable computers to learn from data and improve performance
5. Which of the following is a subset of machine learning?
(a) Deep learning
(b) Data mining
(c) Internet of Things (IoT)
(d) Text translation
Answer: (a) Deep learning

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 2
6. Which approach is based on predefined rules and conditions?
(a) Deep learning
(b) Unsupervised learning
(c) Reinforcement learning
(d) Rule-based approach
Answer: (d) Rule-based approach
7. Which type of AI learning involves training the model with labeled data?
(a) Data compression
(b) Speech synthesis
(c) Image recognition and object detection
(d) Text translation
Answer: (c) Image recognition and object detection
8.. Which type of AI learning is based on trial and error with rewards and penalties?
(a) Reinforcement learning
(b) Clustering algorithm
(c) Learning-based approach
(d) Classification algorithm
Answer: (a) Reinforcement learning

9. An AI agent playing a game and learning from its rewards and penalties is an example of:
a) Supervised Learning b) Unsupervised Learning c)
Reinforcement Learning d) Evolutionary Learning purpose
only.
ANS: c) Reinforcement Learning

10. Which of the following statements is NOT true about supervised learning?
a) Requires labeled data for training.
b) Used for classification and regression tasks.
c) Can be less efficient for large datasets.
d) Often used in image recognition applications.
ANS: c) Can be less efficient for large datasets.

11. In an unsupervised learning scenario, the goal is to:

a) Predict a specific output based on labeled data.
b) Identify patterns and relationships within unlabeled data.
c) Train an AI agent through rewards and penalties.
d) Develop complex neural network architectures.
ANS: b) Identify patterns and relationships within unlabeled data.
LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 3

12. Clustering algorithms are commonly used in unsupervised learning for:

a) Spam filtering
b) Image classification
c) Stock price prediction
d) Grouping similar data points
ANS: d) Grouping similar data points

13. Reinforcement learning is particularly useful for scenarios where:

a) Large amounts of labeled data are available.
b) The desired outcome is clear, but the path to achieve it is unknown.
c) The data is structured and easily categorized.
d) The task requires reasoning and logical deduction.
ANS: b) The desired outcome is clear, but the path to achieve it is unknown.

14. Imagine an AI playing a game and learning to win by trial and error. This is an example
of:
a) Supervised Learning
b) Unsupervised Learning
c) Reinforcement Learning
d) Natural Language Processing
ANS: c) Reinforcement Learning

15. Artificial neural networks are inspired by the structure and function of:
a) The human brain
b) Quantum computers
c) Complex mathematical models
d) High-speed processors
ANS: a) The human brain

16. The process of adjusting the weights in a neural network to improve performance is
called:
a) Activation b) Learning c) Optimization d) Training
ANS: d) Training

17. A neural network with multiple layers of interconnected neurons is called a:

a) Single-layer network
b) Deep Neural Network
c) Linear network
d) Perceptron
LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 4
ANS: b) Deep Neural Network

18. Neural networks are particularly well-suited for tasks involving:

a) Simple calculations and mathematical operations
b) Recognizing patterns in complex data like images and text
c) Performing logical deductions and reasoning tasks
d) Storing and retrieving large amounts of information
ANS: b) Recognizing patterns in complex data like images and text

19. Training a neural network often requires:

a) A small set of labeled data samples
b) A significant amount of data and computational resources
c) A specific set of programming instructions
d) A human expert to guide the learning process
ANS: b) A significant amount of data and computational resources

[Link] dose a perceptron model do in AI?

a) Make random decisions
b) Assigns importance (weights) to factors in decision-making
c) Creates ai hardware
d) Store large amount of data
ANS: b) Assigns importance (weights) to factors in decision-making

ANSWER THE FOLLOWING :

Q1. Difference between Rule-Based and Learning-Based AI Models:

Feature Rule-Based AI Model Learning-Based AI Model

Follows fixed, pre-defined rules given

Definition Learns patterns and rules from data
by humans

Data
No training data required Requires training data to learn from
Requirement

Dynamic – adapts and improves with

Adaptability Static – cannot adapt to new data
new data

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 5
Feature Rule-Based AI Model Learning-Based AI Model

Rule-based chatbot with fixed Q&A Spam email filter that learns from
Example
logic labeled emails

Learning Continuously improves by learning

Does not learn or improve on its own
Capability from data

2. What is Supervised, Unsupervised, and Reinforcement Learning? Explain with examples.

Answer:
1. Supervised Learning:
In supervised learning, the machine is trained using labeled data, where both the input
and the correct output are given. The model learns the relationship between input and
output to make accurate predictions.
Example: A spam email filter is trained on emails labeled as “spam” or “not spam.” It
learns the pattern and classifies new emails accordingly.
2. Unsupervised Learning:
In unsupervised learning, the machine is provided with unlabeled data, and it tries to
find hidden patterns, groupings, or relationships in the data by itself.
Example: An online streaming platform like Netflix groups users based on their watch
history to recommend similar shows.
3. Reinforcement Learning:
In reinforcement learning, the machine learns through trial and error. It takes actions in
an environment, receives rewards or penalties, and learns the best strategies over time.
Example: A self-driving car learning to park by trying different movements and learning
from success or failure.
Q3. What is clustering and how is it different from classification?
Answer:: Clustering is an unsupervised learning technique in which a machine groups similar
data points together based on patterns or features. It works on unlabeled data, and the model
itself finds the structure or categories in the data.

Classification is a supervised learning method where the machine is trained on labeled data
to assign data points into predefined categories or classes.

Difference between Clustering and Classification:

Clustering Classification
Works on unlabeled data Works on labeled data
Groups data based on similarities Assigns data to predefined classes
Unsupervised learning Supervised learning
LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 6
Clustering Classification
Example: Grouping customers by behavior Example: Identifying if an email is spam or not

Q4. Explain neural networks. Also give functions of three layers of neural networks.)
Answer:
A Neural Network is a type of artificial intelligence model that is inspired by how the human
brain works. It consists of layers of interconnected nodes (neurons) that process data and learn
patterns to make decisions or predictions. Neural networks are mainly used in tasks like image
recognition, speech processing, and more.
Functions of the Three Layers of Neural Networks:
1. Input Layer:
o This is the first layer of the network.
o It receives the raw data (e.g., an image or a set of values).
o No processing happens here; it just passes the data to the next layer.
2. Hidden Layer(s):
o This is the middle layer where most processing happens.
o Each node in this layer performs calculations using weights and biases.
o The results go through an activation function and are passed to the next layer.
3. Output Layer:
o This is the final layer of the network.
o It gives the final result or prediction (e.g., identifying an image as a dog or a cat).
o It depends on the type of problem—classification, regression, etc.
Neural networks learn by adjusting weights during training to reduce error and improve
accuracy.
Q5. Differentiate between Classification and Regression Model

Point Classification Model Regression Model

Type of
Predicts categories or labels Predicts continuous values
Output

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 7
Point Classification Model Regression Model

Data Type Works with discrete data Works with continuous data

Predicting house price based on size,

Example Classifying emails as spam or not spam
location, etc.

Used when the result falls into specific Used when the result is a numeric
Use Case
classes or groups value

Q6. Write any two examples of applications that use Neural Networks.
Answer:
1. Facial recognition systems
2. Voice assistants like Siri or Google Assistant
Q7. What is the role of a training dataset and testing dataset in AI modeling?
Answer:
• Training Dataset: Used to teach the AI model by showing examples with known outputs.
• Testing Dataset: Used to evaluate the performance of the trained model by checking its
predictions on new, unseen data.
Q8. What are the sub-categories of Unsupervised Learning? Explain both.
Answer:

Aspect Clustering Association

Group similar data based on common Find relationships or patterns among

Purpose
features items

Type of
Unsupervised Learning Unsupervised Learning
Learning

Output Groups or clusters Association rules (e.g., "if X then Y")

Grouping customers based on purchase People who buy bread also tend to buy
Example
habits butter

Q9. What are the advantages of Learning-Based AI Models over Rule-Based Models?
Answer:

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 8
• Can learn from data and improve over time
• More adaptable to new situations
• Can handle complex problems without manually writing rules
• Performs better with large and varied datasets

[Link] is ANN (Artificial Neural Network)? Explain with an example. (4 Marks)

Answer:
An Artificial Neural Network (ANN) is a machine learning model inspired by the structure and
working of the human brain. It is made up of interconnected layers of neurons: input layer,
hidden layer(s), and output layer.

• Each neuron processes input data, applies weights, and passes output to the next layer.
• ANNs are used to recognize patterns, classify data, and make predictions.

Example: An ANN can be trained to recognize handwritten digits from images, such as those
used in automatic postal sorting.
[Link] is the difference between AI, ML, and DL? Explain with a diagram.
Answer:

Aspect Artificial Intelligence (AI) Machine Learning (ML) Deep Learning (DL)
Enables machines to
Allows machines to learn Uses neural networks to
Definition mimic human
from data learn from large data
intelligence
Scope Broadest concept Subset of AI Subset of ML
Data Not always dependent Requires large datasets and
Requires data for learning
Dependency on data high computation power
Chatbots, robotics, Email filtering, Facial recognition, voice
Example
smart assistants recommendation systems assistants (like Alexa, Siri)

CASE BASE QUESTIONS:

[Link] the type of learning (supervised, unsupervised, reinforcement learning) for the
following case studies and explain why.

a) Case Study 1:
A company wants to predict customer churn based on past purchasing behavior, demographics,
and customer interactions. They have a dataset with labeled examples of customers who
churned and those who did not.
Answer: Supervised Learning
Since the data includes labeled examples (churned or not churned), the model learns from
these labels to make future predictions. This is a classic example of supervised learning where
both input and output are known.

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 9

b) Case Study 2:
A social media platform wants to group users based on their interests and behavior to
recommend relevant content. They have a large dataset of user interactions but no predefined
categories.
Answer: Unsupervised Learning
There are no labels or predefined groups provided. The model has to identify patterns or
clusters on its own. This makes it an unsupervised learning problem, specifically clustering.

c) Case Study 3:
An autonomous vehicle is learning to navigate through a city environment. It receives feedback
in the form of rewards for reaching its destination safely and penalties for traffic violations.
Answer: Reinforcement Learning
This is reinforcement learning because the system learns through rewards and penalties. The
vehicle improves its behavior over time by interacting with the environment and receiving
feedback.

d) Case Study 4:
A healthcare provider wants to identify patterns in patient data to personalize treatment plans.
They have a dataset with various patient attributes but no predefined labels indicating specific
treatment plans.
Answer: Unsupervised Learning
The dataset does not contain labels. The system is expected to find hidden patterns or
groupings in the data. This is typical of unsupervised learning.

e) Case Study 5:
A manufacturing company wants to optimize its production process by detecting anomalies in
sensor data from machinery. They have a dataset with examples of normal and anomalous
behavior.
Answer: Supervised Learning
Since the system has labeled examples of what is considered normal and what is considered an
anomaly, it falls under supervised learning. The model learns from these labeled examples to
detect future anomalies.

[Link] the type of model (classification, regression, clustering, association) for the
following case studies:

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 10
a) Case Study 1:
A bank wants to predict whether a loan applicant will "default" or "non-default" on their loan
payments. They have a dataset containing information such as income, credit score, loan
amount, and employment status.
Answer: Classification Model

b) Case Study 2:
A real estate agency wants to predict the selling price of houses based on various features such
as size, location, number of bedrooms, and bathrooms. They have a dataset containing
historical sales data.
Answer: Regression Model

c) Case Study 3:
A marketing company wants to segment its customer base into distinct groups based on
purchasing behavior for targeted marketing campaigns. They have a dataset containing
information such as purchase history, frequency of purchases, and amount spent.
Answer: Clustering Model

d) Case Study 4:
A grocery store wants to identify associations between different products purchased by
customers to understand which products are commonly bought together. They have a
transaction dataset containing records of items purchased together during each transaction.
Answer: Association Model

Q3.A healthcare provider wants to improve patient care by predicting the length of hospital
stays for different medical conditions. They have a dataset containing patient demographics,
medical history, and treatment details. Identify the model type used in each of the following
tasks:

a) Task: To predict whether a patient will have a short or long hospital stay.
Answer: Classification Model

b) Task: To predict the number of days a patient will stay in the hospital.
Answer: Regression Model

c) Task: To segment patients into groups with similar characteristics for personalized treatment
plans.
Answer: Clustering Model

d) Task: To identify patterns in patient treatments and outcomes.

Answer: Association Model.

LAVANYA PGT(Cs)
PM SHRI KENDRIYA VIDYALAYA, DAVANGERE 11

LAVANYA PGT(Cs)