Course Outcome and Syllabus

Sub code : EC8E401 CIE : 50% Marks Hrs/week : 03

SEE : 50% Marks SEE Hrs : 03 Hours Max. Marks: 100

Course Outcomes On Successful completion of the course.

The students will be able to:

1. To know what is artificial intelligence, why artificial intelligence is important, and will understand problem solving methods

2. Compare various search techniques used in AI, learn about Rules and Rule Chaining.

3. Able to categorize different Constraints and propagations and understand how they solve problems in line-drawing analysis and relative calculation.

4. Demonstrate strategies in formulation problems and Induction Heuristic Techniques and how to repair previously acquired knowledge.

5. Understand how Simulation works in Neural nets, how evolution of Genetic Algorithms works, its pros and cons.

6. Differentiate between mental events and mental objects.

Course Outcomes: On Successful completion of the course the students will be able to:

1. Understand AI and how it is represented in different Semantic Forms.

2. Understand different search techniques, Rules and Rule-based systems.

3. Understand how AI plays games, and to solve Constraint Satisfaction Problems.

4. Solve Machine Learning using Nearest Neighbor, ID Trees and Deep Neural Nets

UNIT 1:

Introduction, to AI? What is Artificial Intelligence. Foundations of AI, The history of AI, Intelligent Agents: Agents and Environments, Good Behaviour-The concept of Rationality, The Nature of Environments, The structure of Agents.

Self Learning Exercise: Turing Test, Alternative to Turing Tests (https://gizmodo.com/8-possible-alternatives-to-the-turing-test-1697983985 Accessed on July 18th, 2021), Introduction to Deep Learnin 8 Hrs

UNIT 2:

Basic Search, Optimal Search – British Museum, Depth First, Breadth First, Hill Climbing and Beam, Branch & Bound and A* Algorithm. Rule and Rule Chaining – Rule-Based deduction systems, Procedures for Forward and Backward chaining, Best First Search

Self Learning Exercise: Deep Sequence Modelling

UNIT 3:

Trees and Adversarial Search, MINMAX Gaming, Alpha-Beta Pruning, Propagation of Probability bounds through Opinion Nets (Constraint Satisfaction Problems).

Self-Learning Exercise: Numeric Constraints and Propagation – Numeric constraints (CryptoArithmetic), Expert Systems in Artificial Intelligence - Javatpoint

UNIT 4:

Learning by Analyzing Differences, Introduction to Learning, Nearest Neighbours, Learning: Identification Trees, Disorders, Support Vector Machines,

Self Learning Excercise (SLE): https://www.youtube.com/watch?v=njKP3FqW3Sk&list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI&index=1

UNIT 5:

Training by Neural Nets, Deep Neural Nets, Back Propagation in NN, Convolution Neural Network (CNN), Grouping un-labelled items using k-means clustering Deep

Self Learning Exercise: Reinforcement Learning (https://tinyurl.com/54tru7nc )

TEXT BOOK:

1. Artificial Intelligence – A Modern approach, (3e) Stuart Russel and Peter Norvig - Pearson

2. Machine Learning in Action: Peter Harrington, Manning Publications, 2012

Reference Books:

1. Decision Support and Business Intelligence System (9e), PEARSON Efraim Turban and et. al.

2. Deep Learning - http://introtodeeplearning.com/2020/index.html

3. Machine Learning and Deep Learning Fundamentals - https://deeplizard.com/learn/video/OT1jslLoCyA

4. Machine Learning Hands-On for Developers and Technical Professionals – Jason Bell, Wiley 2015

Evaluation Pattern:

Module 1 and Module 2 - for 25 marks

Module 3 and Module 4.5 - for 25 marks

Module 4.5+ and Module 5 - for 25 marks

So Total marks from Tests (50 marks)

SEE: 100 marks - Time duration 3 hours ( All the Modules 1 through 5)

SEE QP: 5 Question of 18 Marks each, 10 Marks from Self-Learning Topics