COL333/COL671 - Artificial Intelligence - Autumn 2018
Tuesday, Thursday, Friday 11-11:50 pm in LH 121


Instructor: Mausam
(mausam at cse dot iitd dot ac dot in)
Office hours: by appointment, SIT 402
TAs: (office hours by appointment)

Course Contents

Introduction; philosophy of intelligent agents; uninformed search; heuristic search; local search; constraint satisfaction; logic and satisfiability; adversarial search; decision theory; Markov decision processes; Bayesian networks representation, inference and learning; reinforcement learning; basics of supervised, semi-supervised and unsupervised learning; intro to deep learning; intro to NLP; current research trends.

Schedule

Start End Topics & Lecture Notes Required Readings Additional Resources
Jul 24 Aug 1 Introduction AIMA Chapter 1
Beyond Turing Test
Applications of AI
Benefits/Risks of AI
Introduction to AI: Past, Present & Future
Aug 1 Aug 3 Uninformed search AIMA Chapter 3.1-3.4
Beam Search
Intuition of Search Algorithms
Search Algorithms Performance
Uniform Cost Search vs. Djikstra's
Aug 3 Aug 10 Informed search AIMA Chapter 3.5-3.7
IDA*
Depth First Branch and Bound
A*/IDA* Example
Aug 14 Aug 17 Local search AIMA Chapter 4.1
Stochastic Beam Search
Evolving Monalisa through Genetic Algorithms
Evolving TSP with Genetic Algorithms
Mixability for Genetic Algorithms (pages 66-68)
Aug 15 Aug 29 Programming Assignment 1
Resources
Aug 17Aug 28 Adversarial search AIMA Chapter 5
How Intelligent is Deep Blue?
Minimax Applet
Aug 30 Sep 1 Constraint Satisfaction AIMA Chapter 6 (skip 6.3.3)
Conversion to Binary CSP
NumberJack
Constraint Programming
Aug 31 Sep 17 Programming Assignment 2
Sep 1Sep 13 Logic and Satisfiability AIMA Chapter 7, 8.1-8.3
Sep 13 Sep 14 Phase Transitions and Backdoors Advanced SAT Solvers (Sections 2.3, 2.4)
Phase Transitions
Backdoors
Sep 17 Oct 1 Programming Assignment 3
Resources
Sep 18 Sep 20 Decision Theory AIMA Chapter 16.1-16.3, 16.6

Sep 25 Sep 26 Markov Decision Processes AIMA Chapter 17.1-17.3

Sep 27 Oct 1 Partially Observable Markov Decision Processes AIMA Chapter 17.4
POMDP Tutorial

Oct 1 Oct 9 Agent Architectures AIMA Chapter 2

Oct 9Oct 23 Reinforcement Learning AIMA Chapter 21.1-21.3
TD Learning for Backgammon
Oct 11 Oct 24 Programming Assignment 4
Resources
Oct 25Oct 27 Introduction to Deep Learning and CNNs DL 6, 9.1-9.3

Oct 27 Nov 12 Programming Assignment 5

Oct 30Oct 30 Deep Reinforcement Learning Deep Q Networks

Nov 1 Nov 1 Intro to Probability AIMA Chapter 13
History of Bayes Theorem
Nov 6 Nov 13 Bayesian Networks AIMA Chapter 14.1, 14.2, 14.4, 20.1, 20.2.1
Influence Flow in Bayes Nets
Nov 15Nov 15 Ethics of AI



Wrap Up


Textbooks

Stuart Russell & Peter Norvig, Artificial Intelligence: A Modern Approach,
Prentice-Hall, Third Edition (2009) (required).

Ina GoodFellow, Yoshua Bengio & Aaron Courville, Deep Learning,
MIT Press (2016).

Grading

Assignments: 50%; Minor (each): 10%; Final: 30%; Class participation, online discussions: extra credit.

There will be five programming assignments due approximately every two weeks.

Course Administration and Policies

Cheating Vs. Collaborating Guidelines

As adapted from Dan Weld's guidelines.

Collaboration is a very good thing. On the other hand, cheating is considered a very serious offense. Please don't do it! Concern about cheating creates an unpleasant environment for everyone. If you cheat, you get a zero in the assignment, and additionally you risk losing your position as a student in the department and the institute. The department's policy on cheating is to report any cases to the disciplinary committee. What follows afterwards is not fun.

So how do you draw the line between collaboration and cheating? Here's a reasonable set of ground rules. Failure to understand and follow these rules will constitute cheating, and will be dealt with as per institute guidelines.