COL333/CSL671 - Artificial Intelligence - Autumn 2015
Tuesday, Thursday, Friday 11-11:50 pm in LH108


Instructor: Mausam
(mausam at cse dot iitd dot ac dot in)
Office hours: by appointment, SIT 402
TAs: (office hours by appointment)
Himanshu Jain (csz138519 at cse.iitd.ac.in)
Yashoteja Prabhu (csz138234 at cse.iitd.ac.in)
Neetu Jindal (neetu at cse.iitd.ac.in)
Ankit Rohilla (mcs142118 at cse.iitd.ac.in)
Harinder Pal (mcs142123 at cse.iitd.ac.in)
Kapil Thakkar (mcs142124 at cse.iitd.ac.in)
Madhur Gupta (cs5110282 at cse.iitd.ac.in)
Mayank Raj (cs5110284 at cse.iitd.ac.in)
Shiva Chandra (cs5110296 at cse.iitd.ac.in)
Karan Goel (ee5110555 at iitd.ac.in)
Shreya Rajpal (me2120800 at iitd.ac.in)

Course Contents

Introduction; philosophy of intelligent agents; uninformed search; heuristic search; local search; constraint satisfaction; logic and satisfiability; adversarial search; classical planning; 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; intro to information retrieval; current research trends.

Schedule

Start End Topics & Lecture Notes Required Readings Additional Resources
Jul 23 Jul 31 Introduction AIMA Chapter 1
Beyond Turing Test
Applications of AI
Benefits/Risks of AI
Aug 4 Aug 7 Uninformed search AIMA Chapter 3.1-3.4
Beam Search
Intuition of Search Algorithms
Search Algorithms Performance
Uniform Cost Search vs. Djikstra's
Aug 7 Aug 13 Informed search AIMA Chapter 3.5-3.7
IDA*
Depth First Branch and Bound
A*/IDA* Example
Aug 14 Aug 27 Programming Assignment 1
Resources
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 17 Aug 18 Adversarial search AIMA Chapter 5
How Intelligent is Deep Blue?
Minimax Applet
Poker is Solved!
Aug 27 Aug 28 Classical Planning AIMA Chapter 10
FF Planner
Aug 28 Sep 14 Programming Assignment 2

Sep 3 Sep 3 Decision Theory AIMA Chapter 16.1-16.3, 16.6

Sep 4 Sep 10 Markov Decision Processes AIMA Chapter 17.1-17.3

Sep 11 Sep 11 Heuristic Search for MDPs MDPs Book Chapter 4.1-4.3

Sep 15 Sep 16 Partially Observable Markov Decision Processes AIMA Chapter 17.4
POMDP Tutorial

Sep 16 Sep 29 Programming Assignment 3
Resources
Sep 17Sep 29 Reinforcement Learning AIMA Chapter 21.1-21.3
TD Learning for Backgammon
Oct 1 Oct 6 Bandits and Monte Carlo Tree Search
Monte Carlo Planning (Sections 3.1-3.3)
AIMA Chapter 21.4
UCT for Go
Monte Carlo Planning
Oct 4 Oct 28 Programming Assignment 4
Format Checker
Oct 13Oct 16 Logic and Satisfiability AIMA Chapter 7, 8.1-8.3
Oct 27 Oct 30 Satisfiability Applications and Phase Transitions Advanced SAT Solvers (Section 2.3)
Phase Transitions
Oct 28 Nov 12 Programming Assignment 5

Oct 29 Oct 29 Intro to Probability AIMA Chapter 13
History of Bayes Theorem
Nov 3 Nov 6 Bayesian Networks Representation AIMA Chapter 14.1-14.4
Influence Flow in Bayes Nets
Nov 6 Nov 10 Bayesian Networks Inference and Learning AIMA Chapter 14.5, 20
Log Probabilities
Nov 17Nov 17 Wrap Up


Textbook

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

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.