23AD2001O

ARTIFICIAL INTELLIGENCE &

MACHINE LEARNING
LTPS:3020
SESSION NO: 0
TOPIC: INTRODUCTION TO AI & ML
ARTIFICIAL INTELLIGENCE

• Artificial Intelligence (AI), refers to the development of computer systems

that can perform tasks that would normally require human intelligence, such
as learning, problem-solving, decision-making, and pattern recognition.
• The term “artificial intelligence” was coined in the 1950s by John McCarthy.
• John McCarthy is considered the father of Artificial Intelligence.

2
AI & ML INTRODUCTION

3
APPLICATIONS OF AI & ML

4
ARTIFICIAL INTELLIGENCE AND MACHINE
LEARNING - SYLLABUS
MODULE 1
Introduction to Artificial Intelligence: Overview of AI, history, and
applications; Agents and Environments; Problem Solving through
search: Uninformed Search Algorithms: Breadth-first search,
Depth-first search, Depth Limit search, Iterative deepening
search, Bi-Directional Search; Informed Search: Heuristic search,
Best First Search, A* algorithm, Local Search algorithms: Hill
Climbing Algorithm, Simulated Annealing, Adversarial Search:
Minimax algorithm, Alpha-beta pruning

5
ARTIFICIAL INTELLIGENCE AND MACHINE
LEARNING - SYLLABUS
MODULE 2
Constraint Satisfaction: Problem formulation, Constraint
propagation, Backtracking algorithms, Knowledge Engineering:
propositional Logic, Predicate Logic, Inferencing through
propositional and Predicate Logic: Introduction, Inferencing rules,
Inferencing Mechanisms: Entitlement, Resolution, Lifting,
Reasoning, Implementing inferencing: Forward Checking and
Backward Chaining; Introduction to probability theory,
Introduction to uncertainty Bayes Theorem

6
ARTIFICIAL INTELLIGENCE AND MACHINE
LEARNING - SYLLABUS
MODULE 3
Machine Learning: Introduction to Machine Learning, Types of
Machine Learning; Introduction to Data Preprocessing: Data Cleaning,
Data Splitting, Data Normalization, Data Batching, Data Shuffling,
Overfitting and Underfitting; Performance metrics: Confusion matrix,
Accuracy, F-score, Precession and Recall, Cross Validations;
Supervised learning: Linear regression, Logistic Regression, Naive
Bayes Classification, Bayesian Belief Networks; Decision Trees, KNN;
Support Vector Machines (SVM), Introduction to Ensemble methods.

7
ARTIFICIAL INTELLIGENCE AND MACHINE
LEARNING - SYLLABUS
MODULE 4
Ensemble methods: Bagging: Random Forest, Boosting: XG Boosting,
Ada-Boosting, Unsupervised learning algorithms: K-Means clustering,
Hierarchical Clustering Artificial Neural Networks (ANN): Introduction to
ANN: Weights and Bios, Bios Vs Variance, McCulloch Pits, Perceptron,
Applications of ANN, Types of ANN: Single-Layer Perceptron, Multi-Layer
Perceptron, Feedforward and Backwards ANNs, Recurring RNN, Basics of
ANN: Structure of ANN, Functionality of ANN, Learning ANNs, ANN
techniques: Activation functions, Error computation (Loss Functions),
Error distribution(Optimization), and Prediction using ANN.

8
EVALUTION COMPONENTS
END SEMESTER SUMMATIVE EVALUATION
Evaluation Evaluation Duration
Weightage/Marks CO1 CO2 CO3 CO4 CO5
Type Component (Hours)

End Weightag 6.2

Sem End 25 6.25 6.25 6.25
e 5
Summet Semester 180
ive 40% Exam Max
100 25 25 25 25
Marks
Weightag
Lab End 15 15
e
Semester 180
Max
Exam 50 50
Marks

9
 IN SEMESTER FORMATIVE EVALUATION

Evaluatio
Duratio
Evaluatio n Weightage/ CO
n CO1 CO2 CO3 CO4
n Type Compone Marks 5
(Hours)
nt
In Continuous Weightage 8 8
Semester Evaluation
Summativ - Lab 120
Max Marks 100 100
e Exercise
Evaluation
Total= 28 MOOCs Weightage 10 2.5 2.5 2.5 2.5
90
% Review Max Marks 100 25 25 25 25
Weightage 10 2.5 2.5 2.5 2.5
ALMs 120
Max Marks 100 25 25 25 25

10
 IN SEMESTER SUMMATIVE EVALUATION

Evaluation Evaluation Weightage/Marks Duration CO1 CO2 CO3 CO4 CO5

Type Component (Hours)
In Semester in Weightage 12 90 6 6
Semester Exam-I Max Marks 50 25 25
Summativ
e Semester in Weightage 12 90 6 6
Evaluatio Exam-II Max Marks 50 25 25
n
Total= 32
Lab In Weightage 8 120 8
Semester Max Marks
% 50 50
Exam

11
BOOKS

Text Books:
• Stephen Marsland, “Machine Learning an Algorithmic Perspective”, CRC Press,
(9999).
• Tom M. Mitchell, “MachineLearning”, McGrawHill, 1997.
Reference Books :
• 1. Peter Harrington, “Machine Learning in Action”, Manning Publications
• 2. Ethem lpaydin, “Introduction to Machine Learning”, The MIT Press, (2010).
• 3. Programming Python by Mark Lutz, O'Reilly
• 4. Chun, J Wesley, Core Python Programming, 2 nd Edition Pearson 2007 Reprint

12
WEB LINKS

1. Data Science and Machine Learning:

https://www.edx.org/course/data-science-machinelearning
2. Machine Learning:
https://www.ocw.mit.edu/courses/6-867-machine-learning-fall-2006/

13
SUMMARY:

• AI and ML applications are transforming various domains, including healthcare,

agriculture, robotics, automation, law, medicine, pharmacy, and business
management.
• The potential benefits of these applications include improved efficiency,
reduced costs, and improved decision-making.
• However, there are also potential risks and challenges associated with the use
of AI and ML applications, including privacy concerns, bias, and the need for
ethical guidelines.
• It is important for researchers, policymakers, and practitioners to work
together to develop responsible and ethical AI and ML applications that benefit
society as a whole.

14
SELF ASSESSMENT QUESTIONS

1. Which of the following is not the application of AI?

(a) Self Driving Cars

(b) Medical Image Diagnosis
(c) Supermarket Order processing System
(d) Crop yield Prediction

2. Which of the following are part of AI

(a) Machine Learning

(b) Data Warehousing
(c) Deep Learning
(d) Data Science

15
TERMINAL QUESTIONS

• List some applications of Machine Learning

• How does ML applications differ from AI
applications?
• What are the advantages and disadvantages of
Machine Learning?

16
REFERENCE BOOKS AND WEB LINKS

Text Books:
1) Russel and Norvig, ‘Artificial Intelligence’, third edition, Pearson Education, PHI, (2015)
2) Elaine Rich & Kevin Knight, ‘Artificial Intelligence’, 3nd Edition, Tata McGraw Hill Edition, Reprint
(2008)

Web links:
1. https://www.geeksforgeeks.org/agents-artificial-intelligence/
2. https://www.simplilearn.com/what-is-intelligent-agent-in-ai-types-function-
article
3. https://www.javatpoint.com/turing-test-in-ai
4. https://www.geeksforgeeks.org/turing-test-artificial-intelligence/
5. https://www.section.io/engineering-education/turing-test-in-ai/

17
THANK YOU