Birla Institute of Technology and Science, Pilani

Pilani Campus
Academic Undergraduate Studies

Department of Computer Science and Information Systems

First Semester: 2024-2025
Course Handout: Part-II
Date: 31/July/2024

In addition to part-I (General handout for all courses appended to the timetable) this portion gives
further specific details regarding the course:

Course No. : CS F407

Course Title : Artificial Intelligence
Instructor-in-Charge : Kamlesh Tiwari
(kamlesh.tiwari@pilani.bits-pilani.ac.in)
Instructor : Vishal Gupta
(vgupta@pilani.bits-pilani.ac.in)

1. Objective and Scope of the Course

Artificial Intelligence (AI) is a branch of computer science focused on creating technology that
emulates human cognitive processes in computer systems. The primary objective of AI is to develop
intelligent entities (called agents) capable of mimicking human intelligence traits such as problem-
solving, reasoning, planning, handling uncertainty, and learning. This course introduces students to a
comprehensive set of algorithms and techniques for constructing these intelligent entities. By the end
of the course, students will gain a broad understanding of the AI field. They will learn to identify and
apply AI techniques to solve various problems and critically evaluate new techniques as they emerge.
The course covers essential issues and methodologies for developing computer systems that exhibit
intelligent behavior. Key topics include AI search techniques, ML, game playing, planning, knowledge
representation, reasoning under uncertainty, and reinforcement learning.

2. Course Material
Text Book:

[TB1]: Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach,
Pearson, 4e, Pearson

Reference Books:

[R1]: Deepak Khemani. A First Course in Artificial Intelligence, McGraw Hill

Education (India), 2013
[R2]: Stefan Edelkamp and Stefan Schroedl. Heuristic Search: Theory and
Applications, Morgan Kaufmann, 2011.
[R3]: George F.Luger, Artificial Intelligence, Pearson Education
[R4]: Ben Coppin, Artificial Intelligence Illuminated, Jones and Bartlett Publishers
[R5]: Elaine Rich, Kevin Knight and S. B. Nair, Artificial Intelligence, Third Edition,
McGraw Hill Publishers
[R6]: Dan W Patterson, “Introduction to AI and Expert Systems”, Prentice Hall of India,

Please Do Not Print Unless Necessary

 Birla Institute of Technology and Science, Pilani
Pilani Campus
Academic Undergraduate Studies

New Delhi, 2010

3. Course Plan
Lecture Topic(s) Reference
Introduction: Foundation and History of AI. success stories, CH-01
1-2
risk and benefits. Turing test and its variants.
Intelligent Agents: Agents & Environments, Rational CH-02
3-4 Behavior, Performance Measure, Environment, Actuators,
Sensors (PEAS), Structure of Agents
Problem solving agent: importance of goal, uninformed CH-03
5-6 search strategies, BFS, DFS, Depth limited search, Iterative
deepening depth-first search.
Informed search strategies: Greedy best-first search, A* CH-03+04
algorithm, Heuristic functions, Time & space complexity of
7-9 search algorithms, Local search algorithms: Hill climbing,
Simulated annealing, Local beam search, Partially Observable
Environment
Constraint Satisfaction Problems (CSPs): Definition, CH-05
Modeling real-world problems as CSP, General purpose
10-11
heuristic, Constraint propagation, Backtracking search for
CSPs, Local search for CSPs, Structure of problems
Adversarial Search: game theory, Alpha-Beta Tree search, CH-06
12-13
Monte Carlo Search Tree
Knowledge Representation & Reasoning: CH-07+08+09
Knowledge-based agents, Propositional logic, First-order logic
14-21 (FOL), Inference in FOL, Forward chaining, Backward chaining,
Resolution, Theorem proving & model checking, Knowledge
engineering in FOL.
Quantifying Uncertainty and Probabilistic Reasoning: CH-12+13+14
Bayesian probability & Bayes’ theorem, Naïve Bayes’ model, Class-Notes
Bayesian Belief Networks (BBN), Semantics of BBNs,
22-27 Inference in BBNs
Probabilistic Reasoning over Time: Inference in temporal
models, Hidden Markov Models (HMM), Kalman filters,
Dynamic Bayesian networks
Optimization Models: Reinforcement Learning, Genetic CH-22
28-30 Algorithm, Ant Colony Optimization, Particle Swarm Class-Notes
Optimization,
Machine Learning: Basics, Performance Evaluation, CH-18
Supervised learning, Un-supervised learning, Ensemble Class-Notes
31-34
learning, K-NN, Decision Tree, Random Forest, Linear
Regression, Logistic Regression, SVM
Neural networks: Perceptron, Neuron, activation functions, CH-21
35-36
power of multiple layers Class-Notes
Convolution neural networks (CNNs): convolution, CH-24
37-38 pooling and its variations, different deep CNN architectures - Class-Notes
LeNet, AlexNet, VGG, PlacesNet, DenseNet
39-40 Applications: Applications in vision, speech and natural CH-23+26
language processing, End-to-End Spatial Transform Face Class-Notes
Detection and Recognition, DeepFace and FaceNet, advanced
topics.

Please Do Not Print Unless Necessary

 Birla Institute of Technology and Science, Pilani
Pilani Campus
Academic Undergraduate Studies

4. Learning outcome
Students who complete this course would be able
1. To designing intelligent agents and represent knowledge in inference-based problem solving
2. To apply probability theory to describe and model agents operating in uncertain environments
3. To optimize computation models for processing real world application of intelligent agents
4. To understand the importance of general purpose solution with end-to-end learning.
5. To represent problem and derive reasoning using logical inferences

5. Evaluation Scheme
SN Evaluation Component Marks Information
1. Mid-Semester Test: 30% Closed Book
FN1 - Oct 04, 2024 (Expected duration 90 Min)
2. Quiz: 5% Closed Book
One in Number (Expected duration 40 Min)
3. Term Project: 25% Continuous Evaluation. Would be
Could be done individually or in groups of evaluated based on the Proposal
two/three. A list of problems would be provided
(3%), Demonstration (7%+10%)
by the instructor. Require coding to develop and
generate results. report/viva/presentation (5%).
4. Comprehensive Exam: 40% Partially Open Book
FN - Dec 05, 2024 (Expected duration 180 Min)

6. Honor Code
All component are individual until specifically mentioned. Plagiarism in any form shall be tolerated
(we would be using appropriate software tools). Student shall be awarded ZERO marks and case
may be reported to the appropriate committee of the Institute for appropriate action. Every
component is individual until specifically specified.

7. Notices
All notices would be put on course website: www.ktiwari.in/ml and NALANDA. Submissions
would be through NALANDA.

8. Make-up Policy
To be granted only in case of serious illness or emergency, on case to case basis for the
Comprehensive Exam only.

9. Chamber Consultation Hours

Tuesday 10-11 AM. Seek appointment if you wish to meet online.

Instructor-in-Charge

Please Do Not Print Unless Necessary