Download as pdf or txt
Download as pdf or txt
You are on page 1of 90

DATA DRIVEN ARTIFICIAL

INTELLIGENT SYSTEMS
22AD2001R

STUDENT ID: ACADEMIC YEAR: 2023-24


STUDENT NAME:
Table of Contents

1. Session 01: Introductory Session .............................................................................................. NA


2. Session 02: Simple reflex agent for a vacuum cleaner ................................................................ 1
3. Session 03: Breadth First Search (BFS) ........................................................................................ 9
4. Session 04: A* search algorithm to solve 8-puzzle problem ..................................................... 17
5. Session 05: TSP using Hill climbing algorithm ........................................................................... 25
6. Session 06: Constraint satisfaction problem ............................................................................. 30
7. Session 07: Knowledge representation using FOL .................................................................... 37
8. Session 08: Bayesian network Inference algorithm .................................................................. 44
9. Session 09: k-NN algorithm ....................................................................................................... 51
10. Session 10: Simple Feedforward Neural Network .................................................................... 58
11. Session 11: Data Visualization Techniques with standard Dataset ........................................... 66
12. Session 12: Medical Image Classification using CNN ................................................................ 73
13. Session 13: Decision Tree .......................................................................................................... 80
A.Y. 2023-24 LAB CONTINUOUS EVALUATION

S.No. Date Experiment Name Pre- In-Lab (25M) Post- Viva Total Faculty
Lab Program/ Data and Analysis & Lab Voce (50M) Signature
(10M) Procedure Results Inference (10M) (5M)
(5M) (10M) (10M)
1. Implement a simple reflex agent for a
vacuum cleaner.
Implement Breadth-First Search (BFS) to
2.
solve a maze problem
Implement A* search algorithm to solve
3.
the 8-puzzle problem
Implement the Hill Climbing
4. algorithm to solve the Traveling
Salesman Problem (TSP).
Implement the backtracking algorithm
5.
to solve the N-Queens problem.
Create a knowledge base using first-
6.
order logic for a family tree.
Implement the Bayesian network
7.
inference algorithm.
Implement the k-Nearest Neighbours
8.
(kNN) algorithm for classification.
Implement a simple feedforward
9. neural network with one hidden layer
for classification.
Construct a Python Program to Show
various Data Visualization
10.
Techniques using Existing Well-
Known Dataset
S.No. Date Experiment Name Pre- In-Lab (25M) Post- Viva Total Faculty
Lab Program/ Data and Analysis & Lab Voce (50M) Signature
(10M) Procedure Results Inference (10M) (5M)
(5M) (10M) (10M)
Construct a CNN Model for Medical
11.
Image Classification.
Implement the Decision Tree
12.
algorithm for classification.
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 1

Title: Simple reflex agent for a vacuum cleaner

Aim/Objective:

Implement a simple reflex agent for a vacuum cleaner. Description: Students will create a simple reflex
agent to clean a grid-based environment. The agent will perceive the status of the current cell and
decide whether to clean, move, or do nothing.

Description:

Students will create a simple reflex agent to clean a grid-based environment. The agent will perceive
the status of the current cell and decide whether to clean, move, or do nothing.

Pre-Requisites:

The program can be implemented in a programming language of choice, such as Python, Java, or C++.
The simplicity of the agent's decision-making process makes it an introductory exercise in artificial
intelligence, allowing students to understand the concept of reflex agents and their application in
autonomous systems.

Pre-Lab:

1. What is the purpose of implementing a reflex agent for a vacuum cleaner in this lab?

2. What is a reflex agent, and how does it differ from other types of intelligent agents?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 1 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. Describe the grid-based environment in which the vacuum cleaner agent will operate. How is it
structured?

4. What are the possible states that a cell in the grid-based environment can have? How are these
states represented?

5. What are the available actions that the vacuum cleaner agent can take in response to the current
cell's status?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 2 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab:

Experiment 1: Write a python program to implement a simple reflex agent for a vacuum cleaner in a
single-room environment with two locations (A and B).

 Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 3 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 4 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Sample VIVA-VOCE Questions (In-Lab):

1. What is the purpose of creating a simple reflex agent for a vacuum cleaner?
2. How does the agent perceive the status of the current cell in the grid-based environment?
3. What are the possible actions that the agent can take in response to the current cell's status?
4. How does the agent decide whether to clean, move, or do nothing based on the current cell's
status?
5. Can you explain the concept of a reflex agent in the context of this vacuum cleaner
implementation?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 5 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment 1: Implement a Random Movement Reflex Agent (introduce a random movement


reflex agent that selects a random direction (left, right, up, or down) regardless of the
location's status. Allows the vacuum cleaner to explore the environment more dynamically.)

 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 6 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 7 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 8 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 2

Title: Breadth First Search (BFS)

Aim/Objective:

BFS is an uninformed search method that aims to expand and examine all nodes of a graph or
combination of sequences by systematically searching through every solution.

Description:

Students will create a simple graph and traverse the graph using Breadth-first search. BFS is a graph
traversal algorithm that starts traversing the graph from the root node and explores all the
neighbouring nodes. Then, it selects the nearest node and explores all the unexplored nodes.

Pre-Requisites:

 Basic understanding of search algorithms.


 Familiarity with Python programming language.
 Knowledge of Graph traversing.

Pre-Lab:

1. What is Breadth-First Search (BFS)? Explain the basic idea behind BFS and how it explores a graph
or a maze.

2. What data structure(s) are commonly used in BFS? Describe their purpose and how they help in
implementing the algorithm efficiently.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 9 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. How can a grid-based maze be represented in a data structure? Discuss the options and explain
which one you would choose for this implementation.

4. What are the steps involved in implementing BFS to solve a maze problem? Provide a high-level
overview of the algorithm.

5. What is the purpose of marking visited cells in BFS? How can you keep track of visited cells
efficiently during the traversal process?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 10 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab:

Experiment 1: Implement Breadth-First Search using Python and find to move from node S to node G
for the graph below using BFS.

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 11 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 12 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Sample VIVA-VOCE Questions (In-Lab):

1. What is the purpose of the Breadth-First Search (BFS) algorithm?


2. How does BFS work in solving a maze problem?
3. What data structure(s) are typically used to implement BFS for maze solving, and why?
4. Can you explain the steps involved in implementing BFS for a maze problem?
5. How do you represent a maze in memory when using BFS?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 13 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment 1: Write algorithms for Breadth First Search. Implement BFS on the given tree.

 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 14 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 15 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 16 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 3

Title: A* search algorithm to solve 8-puzzle problem

Aim/Objective:

The aim of this experiment is to implement the A* search algorithm to solve the 8-puzzle problem.
Students will learn how the A* search algorithm works and its application in finding an optimal solution
to the 8-puzzle problem.

Description:

In this experiment, students will explore the A* search algorithm, a popular informed search algorithm
used in artificial intelligence. The 8-puzzle problem involves a 3x3 grid with 8 numbered tiles and one
empty space. The goal is to rearrange the tiles from a given initial state to a desired goal state by
sliding the tiles into the empty space.

Students will implement the A* search algorithm using heuristics such as the Manhattan distance to
estimate the cost of reaching the goal state from each possible move. By considering both the cost
incurred so far and the estimated cost to reach the goal, A* search algorithm intelligently explores the
state space to find an optimal solution to the 8-puzzle problem.

Pre-Requisites:

 Basic understanding of search algorithms.


 Familiarity with Python programming language.
 Knowledge of the 8-puzzle problem and its rules.

Pre-Lab:

1. What is the 8-puzzle problem?

2. What is the goal of the 8-puzzle problem?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 17 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. What is the A* search algorithm, and how does it work?

4. What is a heuristic function, and why is it important in A* search?

5. What is the Manhattan distance heuristic, and how is it calculated in the context of the 8-
puzzle problem?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 18 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab:

Program 1: implement the A* search algorithm using a priority queue.

Description: The 8-puzzle problem involves a 3x3 grid with 8 numbered tiles and one empty space.
The goal is to rearrange the tiles from a given initial state to a desired goal state by sliding the tiles
into the empty space. The A* search algorithm is used to find an optimal solution by considering both
the cost incurred so far and the estimated cost to reach the goal state using a heuristic function.

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 19 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 20 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Sample VIVA-VOCE Questions (In-Lab):

1. What is the purpose of using the A* search algorithm in the 8-puzzle problem?
2. Explain the role of the heuristic function in the A* search algorithm.
3. How is the Manhattan distance calculated in the context of the 8-puzzle problem?
4. What are some advantages and limitations of the A* search algorithm?
5. Can the A* search algorithm guarantee finding an optimal solution in all cases?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 21 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 22 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment: Compare and contrast the A* search algorithm with other search algorithms such as
breadth-first search or depth-first search. What are the advantages of using the A* search
algorithm in terms of finding an optimal solution and efficient exploration of the state space?
 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 23 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 24 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 4

Title: Traveling Salesman Problem (TSP) using Hill climbing algorithm

Aim/Objective:

To Implement the Hill Climbing algorithm to solve the Traveling Salesman Problem (TSP).

Description: Students will implement the Hill Climbing algorithm to find an approximately optimal
solution to the TSP, visiting all cities and returning to the starting point.

Pre-Requisites:

Understanding of the Traveling Salesman Problem, Familiarity with graph representation, Knowledge
of the Hill Climbing algorithm, Basics of heuristics

Pre-Lab:

1. Define in detail about Heuristic Search technique in AI?

2. Give details about different types of heuristic search algorithms

3. List out the steps to be followed for implementing hill climbing search algorithm in AI?
Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 25 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab:

Experiment: To Implement the Hill Climbing algorithm to solve the Traveling Salesman Problem (TSP).

Description: Implement the Hill Climbing algorithm to find an approximately optimal solution to the
TSP, visiting all cities and returning to the starting point.

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 26 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

VIVA-VOCE Questions (In-Lab):

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 27 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

1. What is TSP Travelling salesman problem algorithm?


2. What is the purpose of hill climbing algorithm?
3. What is the hill climbing approach to solve the TSP problem?
4. Why is the hill climbing algorithm best to deal with the travelling salesman problem?
5. List out the constraints of travelling salesman problem?

Post-Lab:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 28 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment: Use the function hillclimbing() below implements the stochastic hill climbing local search
algorithm.

Description: Students will implement stochastic hill climbing local search algorithm. It takes the name
of the objective function, bounds of the problem, number of iterations, and steps size as arguments
and returns the best solution and its evaluation.

 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 29 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 30 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 5

Title: Constraint satisfaction problem

Aim/Objective:

Constraint Satisfaction Problems Lab Exercise, Implement the backtracking algorithm to solve the N-
Queens problem.

Description: Students will implement the backtracking algorithm to find a solution for the N-Queens
problem, where N queens are placed on an NxN chessboard so that no two queens threaten each
other.

Pre-Requisites:

Basic programming knowledge, Understanding of the N-Queens problem, Backtracking algorithm,


Recursion

Pre-Lab:

1. What is constraint satisfaction problem in AI with example?

2. What are the basic components of constraint satisfaction problem?

3. What are the applications of CSP in AI?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 31 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab:

Implement the backtracking algorithm to solve the N-Queens problem.

Description: The N-Queens problem involves placing N queens on an NxN chessboard in such a way
that no two queens threaten each other, i.e., no two queens share the same row, column, or diagonal.
Use the backtracking algorithm to systematically explore and backtrack from invalid solutions to find
a valid placement of queens on the chessboard.

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 32 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 33 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Sample VIVA-VOCE Questions (In-Lab):

1. What are the types of constraint satisfaction problem in AI?


2. Which algorithm is used in constraint satisfaction problem?
3. What is the n-queens problem?
4. How backtracking can be used to solve n-queens problem?
5. Which algorithm can be used to solve the N-Queen problem?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 34 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment: Implement Constraint Satisfaction Problems (CSP) using heuristic search algorithm.

Description: Implement a Constraint Satisfaction Problem (CSP) using a heuristic search algorithm to
solve a puzzle where a sequence of numbers, typically integers, is arranged in a square grid, and the
numbers in each row, column, and diagonal must add up to a constant known as the Magic Constant?
The goal is to find a solution that satisfies all constraints while minimizing the search space using
heuristics.

 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 35 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Experiment 6

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 36 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Title: Knowledge representation using FOL

Aim/Objective:

Create a knowledge base using first-order logic for a family tree.

Description:

Students will create a knowledge base using first-order logic to represent facts about a family tree,
such as parent, sibling, and grandparent relationships, and write a function to answer queries about
these relationships.

Pre-Requisites:

Understanding of First-Order Logic, Knowledge of Family Tree Terminology, Proficiency in Predicate


Logic Notation, Familiarity with Logical Inference and Querying.

Pre-Lab:

1. What is first-order logic, and how does it differ from propositional logic?

2. What are the main components of first-order logic, such as predicates, functions, constants, and
variables?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 37 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. Explain how predicates can be used to represent relationships in a family tree.

In-Lab:

Create a knowledge base using first-order logic for a family tree.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 38 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Description: Students will create a knowledge base using first-order logic to represent facts about a
family tree, such as parent, sibling, and grandparent relationships, and write a function to answer
queries about these relationships.

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 39 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Sample VIVA-VOCE Questions (In-Lab):

1. What is first-order logic in AI?


2. What are first-order logic examples?
Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 40 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. What is an example of a logical sequence?


4. Differentiate between a fact and a predicate with syntax.
5. Differentiate between knowledgebase and Rule base approach.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 41 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment: Write a prolog program to find whether a city belongs to a state or not?

 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 42 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 43 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 7

Title: Bayesian network inference algorithm

Aim/Objective:

Implement the Bayesian network inference algorithm.

Description:

Description: Students will implement the Bayesian network inference algorithm to compute the
probability of a specific event, given a set of evidence, a Bayesian network structure, and conditional
probability tables.

Pre-Requisites:

 Basic understanding of probability theory, conditional probability, and Bayesian networks.


 Familiarity with programming concepts and basic knowledge of Python programming
language would be beneficial.

Pre-Lab:

1. What is Bayesian network inference algorithm?

2. What is an example of Bayesian network inference?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 44 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. Explain the concept of prior probability and posterior probability.

4. Discuss the importance of evidence in Bayesian network inference.

In-Lab:

Implement the Bayesian network inference algorithm.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 45 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 46 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 47 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

VIVA-VOCE Questions (In-Lab):

1. Elaborate Bayesian network inference


2. Elaborate Local Markov Property and Conditional Probability
3. Calculation of Joint Probability Distribution
4. Describe Bayesian Networks in Spam Filtering, Semantic Search, Information Retrieval.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 48 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment 1: Parameter Learning: Implement the algorithm to learn the parameters of a Bayesian
network from data.
 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 49 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 50 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 8

Title: k-Nearest Neighbours (kNN) algorithm

Aim/Objective:

Implement the k-Nearest Neighbours (KNN) algorithm for classification.

Description:

Students will implement the KNN algorithm to classify a set of data points based on their features and
labels and predict the label for a new data point.

Pre-Requisites:

 Basic understanding of machine learning concepts, including classification algorithms and


distance metrics.
 Familiarity with programming concepts and basic knowledge of Python programming
language

Pre-Lab:

1. Define the k-Nearest Neighbours (KNN) algorithm and its purpose in classification tasks.

2. Explain the concept of distance metrics and their importance in the KNN algorithm.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 51 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. Discuss the impact of the parameter k on the performance of the KNN algorithm.

4. Describe the training and testing phases in the KNN algorithm.

5. Discuss the advantages and limitations of the KNN algorithm compared to other classification
algorithms.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 52 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab:

Implement the k-Nearest Neighbours (KNN) algorithm for classification.

Description: Students will implement the KNN algorithm to classify a set of data points based on their
features and labels and predict the label for a new data point.

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 53 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 54 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

VIVA-VOCE Questions (In-Lab):

1. What is the k-nearest neighbours (k-NN) algorithm used for?


2. Describe the process of training a k-NN model.
3. How does the k-NN algorithm handle categorical features or attributes?
4. What are the limitations or challenges associated with the k-NN algorithm?
5. How does the k-NN algorithm make predictions or classify instances?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 55 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment 1:

1. Examine the accuracy, precision, recall, F1 score, or any other relevant measures.

2. Identify possible enhancements to the k-NN algorithm or its implementation.

3. Consider how alternative distance metrics or feature selection methods might improve the
classifier's performance.

 Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 56 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Experiment 9
Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 57 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Title: Simple Feedforward Neural Network

Aim/Objective:

Implement a Simple Feedforward Neural Network with One Hidden Layer for Classification

Description:

The aim of this lab experiment is to implement a simple feedforward neural network with one hidden
layer for classification. Students will learn how to build and train a neural network model for
classification tasks and understand the fundamentals of neural network architecture.

Pre-Requisites:

 Basic understanding of machine learning concepts, including neural networks and


classification algorithms.
 Familiarity with programming concepts and basic knowledge of Python programming
language

Pre-Lab:

1. What is a feedforward neural network, and how does it work for classification tasks?

2. Describe the structure and components of a simple feedforward neural network with one
hidden layer.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 58 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. What is the role of activation functions in a neural network? Provide examples of commonly
used activation functions.

4. Explain the concept of backpropagation and how it is used to train a neural network.

In-Lab:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 59 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Implement a simple feedforward neural network with one hidden layer for classification.

Description: Students will implement a simple feedforward neural network with one hidden layer to
classify a set of data points based on their features and labels.

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 60 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

VIVA-VOCE Questions (In-Lab):

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 61 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

1. What is the purpose of a hidden layer in a feedforward neural network?


2. Explain the concept of activation functions and their role in neural networks.
3. How does backpropagation work in training a neural network? What problem does it solve?
4. What are the key steps involved in building and training a feedforward neural network?
5. Discuss any regularization techniques that can be used to prevent overfitting in a neural
network.

Post-Lab:

Experiment 1: Implement a feed forward neural network that works as a parity function.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 62 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Description: The parity function determines whether the number of ones in a binary sequence is odd
or even. For instance, let's consider a 4-bit binary sequence. If the number of ones in the sequence is
odd, the output should be 1 (odd parity). If the number of ones is even, the output should be 0 (even
parity).

 Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 63 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 64 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 65 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 10

Title: Data Visualization Techniques with standard Dataset

Aim/Objective:

Construct a Python Program to Show various Data Visualization Techniques using Existing Well Known
Dataset

Description:

The aim of this experiment is to implement various data visualization techniques using an existing
well-known dataset. Students will gain hands-on experience in visualizing data to uncover patterns,
trends, and insights.

Pre-Requisites:

 Basic understanding of programming concepts and data manipulation.


 They should also be familiar with fundamental data visualization concepts and libraries such
as Matplotlib or Seaborn.

Pre-Lab:

1. What is data visualization, and why is it important in data analysis?

2. Describe the different types of data visualizations commonly used, such as bar charts, line
plots, scatter plots, histograms, and pie charts.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 66 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. What are the key factors to consider when choosing a suitable data visualization technique
for a given dataset?

4. Explain the concept of exploratory data analysis (EDA) and how data visualization plays a
crucial role in this process.

5. Discuss the benefits and limitations of using well-known datasets for data visualization
experiments.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 67 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab: Perform sentiment analysis on a dataset of movie reviews.

Description: Use an RNN model to classify the reviews as positive or negative. Evaluate the model's
performance using appropriate evaluation metrics and visualize the results using confusion matrix and
classification report.

Dataset: dataset for sentiment analysis is the "IMDb Movie Review Dataset." It contains a collection
of movie reviews, along with their corresponding sentiment labels (positive or negative).

Link: https://www.kaggle.com/datasets/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews.

Procedure/Program:

 Data and Results:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 68 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 69 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

VIVA-VOCE Questions (In-Lab):

1. How does an RNN differ from other types of neural networks in handling sequential data?
2. What is the purpose of word embeddings in text classification using RNNs?
3. How can you handle overfitting in an RNN model during text classification?
4. Explain the concept of backpropagation through time (BPTT) in RNNs.
5. What are the advantages and limitations of using RNNs for text classification?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 70 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Experiment 1: Build an RNN model to classify news articles into different topics such as sports, politics,
technology, etc.

Description: Use a suitable dataset for topic classification and pre-process the data accordingly. Train
the RNN model, evaluate its performance, and analyse the classification results.

Dataset: One widely used dataset for topic classification is the "20 Newsgroups dataset." It contains a
collection of newsgroup posts, where each post belongs to one of 20 different topics or categories.

Link: https://www.kaggle.com/datasets/crawford/20-newsgroups.

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 71 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 72 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 11

Title: Medical Image Classification using CNN

Aim/Objective:

The aim of this experiment is to implement a Convolutional Neural Network (CNN) model for medical
image classification. Students will learn how to build and train a CNN model to classify medical images
accurately.

Description:

In this experiment, students will work with a dataset of medical images and develop a CNN model to
classify these images into different categories or classes. They will gain insights into the application of
deep learning techniques in the field of medical image analysis and understand the importance of
accurate classification for diagnosis and treatment.

Pre-Requisites:

 Basic understanding of deep learning concepts, neural networks, and image classification
algorithms.
 They should also be familiar with programming in Python and the Keras or TensorFlow library.

Pre-Lab:

1. Read and understand the basic concepts of CNNs, including convolutional layers, pooling
layers, and fully connected layers.

2. Select a suitable dataset for image classification.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 73 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. Pre-process the dataset as needed, including resizing images, normalizing pixel values, and
splitting the data into training and testing sets.

4. Evaluate the trained model on the pre-processed testing data.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 74 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab: Construct a CNN Model for Medical Image Classification. Consider Breast Cancer dataset for
Classification.

Data set link: https://www.kaggle.com/datasets/yasserh/breast-cancer-dataset

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 75 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 76 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

VIVA-VOCE Questions (In-Lab):

1. What is medical image classification?


2. What are Convolutional Neural Networks (CNNs)?
3. What are activation functions in CNNs? Give examples.
4. How does the backpropagation algorithm work in CNNs?
5. What is the role of fully connected layers in CNNs?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 77 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Case Study 1: Histopathological Breast Cancer Image Classification

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 78 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 79 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Experiment 12

Title: Decision Tree

Aim/Objective:

The aim of this experiment is to implement the Decision Tree algorithm for classification. Students will
learn how to build a Decision Tree model to classify data based on certain features and evaluate its
performance.

Description:

In this experiment, students will work with a dataset containing labelled examples and implement the
Decision Tree algorithm for classification. They will learn the process of building a Decision Tree model
by recursively partitioning the data based on different features and selecting the best split criteria.
The importance of feature selection, node purity measures, and pruning techniques will also be
explored.

Pre-Requisites:

 Students should have a basic understanding of classification algorithms, supervised learning,


and basic programming concepts.
 They should be familiar with Python programming and have knowledge of libraries such as
scikit-learn or any other suitable library for implementing Decision Trees.

Pre-Lab:

1. What is the Decision Tree algorithm, and how does it work?

2. Explain the concepts of entropy and information gain in the context of Decision Trees.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 80 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

3. Describe the process of building a Decision Tree model using the ID3 or C4.5 algorithm.

4. Discuss the advantages and limitations of Decision Trees as a classification algorithm.

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 81 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

In-Lab: Implement the Decision Tree algorithm for classification.


Description: Students will implement the Decision Tree algorithm to classify a set of data points based
on their features and labels.

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 82 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

 Analysis and Inferences:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 83 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

VIVA-VOCE Questions (In-Lab):

1. Why is decision tree algorithm very important in classification?


2. Why is pruning done in decision tree algorithm?
3. Define gini index. What is its function in decision tree algorithm?
4. What is information gain?
5. What is “Entropy”? and What is its function?

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 84 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

Post-Lab:

Compare the performance of the Decision Tree algorithm with other classification algorithms, such as
Naive Bayes or k-Nearest Neighbours.

Procedure/Program:

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 85 of 89
Experiment # <TO BE FILLED BY STUDENT> Student ID <TO BE FILLED BY STUDENT>
Date <TO BE FILLED BY STUDENT> Student Name <TO BE FILLED BY STUDENT>

 Data and Results:

Evaluator Remark (if Any):

Marks Secured: _____out of 50

Signature of the Evaluator with Date

Course Title Data Driven Artificial Intelligent Systems ACADEMIC YEAR: 2023-24
Course Code(s) 22AD2001R Page 86 of 89

You might also like