ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING

Course Code 22CSG53 Credits 4

Hours/Week (L-T-P-S) 3-0-2-0 CIE Marks 50
Total Teaching Hours 52 SEE Marks 50
Exam Hours 3 Course Type Integrated
Course Component Engineering science
COURSE LEARNING OUTCOMES
Students will be able to:
1. Comprehend the fundamentals of AI, and principles of ANN and ML
2. Investigate applications and apply AI techniques logically in expert systems.
3. Analyze the given problems and design for solutions using AI/ML techniques.
4. Effectively apply ML algorithms for appropriate applications and evaluate effectively.
5. Develop critical thinking and problem-solving skills by applying AI/ML techniques to real-world
datasets, and effectively communicate the results and insights derived from these models.
COURSE CONTENTS
UNIT -1- (10 Hours)
Introduction. Why study AI? What is AI? The Turing test. Rationality. Branches of AI. Brief history of AI.
Challenges for the future. What is an intelligent agent? Doing the right thing (rational action). Performance
measure. Autonomy. Environment and agent design. Structure of Agents. Agent types.
Uninformed Search - Depth-first. Breadth- first. Uniform-cost. Depth-limited. Iterative deepening. Examples.
Informed search – Best-first. A* search. Heuristics.
UNIT -2- (12 Hours)
Game Playing - The minimax algorithm. Resource limitations. Alpha-beta pruning. Constraint satisfaction.
Node, arc, path, and k-consistency. First Order Logic – Knowledge -based agents. Logic and representation.
Propositional (boolean) logic– Inference in propositional logic: Propositional vs First order Inference, and
lifting, a simple forward chaining algorithm, a backward chaining algorithm. Probabilistic Reasoning:
Representing knowledge in a uncertain domain, the semantics of Bayesian Networks, Efficient representation
of conditional distributions.
UNIT -3- (10 Hours)
Introduction to Machine Learning: Overview of machine learning, Types of machine learning: supervised,
unsupervised, and reinforcement learning, Bias-variance tradeoff, Model evaluation and performance metrics,
Overfitting and underfitting
Supervised Learning Models: Linear regression, logistic regression; Bayesian Leaning Bayes theorem and
example, Naïve Bayes Classifier and example.
UNIT -4- (10 Hours)
Support Vector Machine: Optimal separation, Kernels, The Support Vector Machine Algorithm.
Artificial Neural Networks: Introduction, Artificial Neural Networks (ANN), biological neural networks,
Basic building blocks of ANN, ANN terminologies, McCulloch-Pitts Neuron Model, Hebb Net. Perceptron
Networks: Single Layer Perceptron, Multilayer Perceptron Networks, back propagation of error, derivation
and learning algorithm.
UNIT -5- (10 Hours)
Unsupervised Learning: Clustering algorithms: k-means, hierarchical clustering
Gaussian Mixture Models (GMMs), Dimensionality reduction: Principal Component Analysis (PCA), Anomaly
detection, Evaluation and validation of unsupervised learning models

TEXTBOOKS
SINO Unit Textbook Title Author(s) Publisher(s) Edition/Year of
Publication
1. 1,2 Artificial Stuart J. Russell and Pearson 3rd Edition, 2018
Intelligence-A Peter Norvig
Modern Approach
 2 1,2 Introduction to S N Sivanandam, S The McGraw-Hill 2017
Neural Networks Sumathi, and S N Companies
using Matlab6.0 Deepa,
3 3,4 Machine Learning, Stephan Marsland, CRC Press 2nd Edition, 2015
An algorithmic
Perspective, CRC
Press
4 1,2 Introduction to Ethem Alpaydin PHI Learning Pvt. 3rd Edition, 2014
Machine Learning Ltd
5 5 Machine Learning Tom M. Mitchell McGraw-Hill 2013
Education
(INDIAN EDITION)
REFERENCE BOOKS
1 1,2 Artificial Elaine Rich,Kevin McGraw-Hill 3rd Edition, 2013
Intelligence Knight
2 3,4 Principles of Nils J. Nilsson Elsevier ISBN-
Artificial 13:9780934613101
Intelligence
3 5 Neural Rajasekharan and PHI Publication 2004
Networks,Fuzzy G.A.Vijayalakshmipa
logic, Genetic i
algorithms:
synthesis and
applications
ONLINE RESOURCES
Topic/Title Link
Introduction. https://builtin.com/artificial-intelligence
Uninformed Search
Informed search
Game Playing - https://ebooks.inflibnet.ac.in/itp6/chapter/game-playing-algorithms/
Probabilistic Reasoning
Artificial Neural Networks: https://www.scribd.com/document/446547093/132618915-neural-
network-using-matlab-
sumathi-and-sivanandam-pdf
Training Models: Support Vector https://cloud.google.com/vertex-ai/docs/training-overview
Machine
Unsupervised Learning
Linear Models and Regression
Genetic Algorithms : https://www.cin.ufpe.br/~cavmj/Machine%20-%20Learning%20-
Evaluating Hypothesis %20Tom%20Mitchell.pdf
COURSE ASSESSMENT METHOD
Continuous Internal Evaluation (CIE):
The following weightages for CIE(Continuous Internal evaluation) will be followed for the course
MSE1 40%(12M)+MSE2 40%(12M)+MSE3 20% (6M) =30 Marks
Quiz- 10 Marks
Course project- 10 Marks
Total- 50 Marks

Semester End Examination (SEE):

SEE Exam: Max. Marks=100 Marks weightage 50%

LAB Assessment
Programming Implementation/Assignment- 30 Marks
Lab Test- 20 Marks
Viva - 10 Marks
Total- 50 Marks
PEDAGOGY
 • Lecture using Black board and chalk
• Presentations
• Programing sessions

LABORATORY EXERCISES
SINO
1 We have the Map of Romania. In this map, the distance between various places in
Romania is given. If we have to reach from one place to another place there exist several
paths. Write a Python Program to find the shortest distance between any two places using
a A* search algorithm.

2 Simulate the smart vacuum cleaner agent that cleans rooms size of n * n. The Agent can
move Up, Down, Left, Right. calculate performance each round.

3 Write a program to implement Alpha Beta pruning in Python. The algorithm can be applied to any
depth of tree by not only pruning the tree leaves but also the entire subtree. Order the nodes in the
tree such that the best nodes are checked first from the shallowest node.
4 Implementation of Tic Tac Toe game here ,the player needs to take turns marking the spaces in a
3x3 grid with their own marks, if 3 consecutive marks (Horizontal, Vertical,Diagonal) are formed
then the player who owns these moves get won. Noughts and Crosses or X’s and O’s abbreviations
can be used to play.

5 Write a program to implement McCulloch-Pitts algorithms, for realizing the

AND/OR/XOR/ANDNOT logic functions.
6 Implement the Perceptron Learning single layer Algorithm by Initializing the weights and
threshold. Execute the code and check, how many iterations are needed, until the network
converge.
7 Demonstrate the working of SVM classifier for a suitable data set
8 Demonstrate the working of k-means clustering algorithm with customer dataset.

CO-PO-PSO MAPPING
PO
CO PSO1 PSO2 PSO3
1 2 3 4 5 6 7 8 9 10 11 12
1 - 3 3 3 - - - - - - - - 3 3 3
2 2 3 3 3 3 - - - 3 3 - - 3 3 3
3 2 3 3 3 3 - - - 3 3 - - 3 3 3
4 2 3 3 3 3 - - - 3 3 - - 3 3 3
5 2 3 3 3 3 - - - 3 3 - - 3 3 3
CL 2 3 3 3 3 - - - 3 3 - - 3 3 3