CSL333/CSL671 - Artificial Intelligence - Spring 2014
Tuesday, Wednesday, Friday 5-5:50 pm in IVLT3


Instructor: Mausam
(mausam at cse dot iitd dot ac dot in)
Office hours: by appointment, Bharti 430
TAs: (Office hours: Tuesday/Friday 4-5 pm, GCL)
Siddharth Bora, siddharth.nyx AT gmail.com
Sudhanshu Shekhar, hi.sudhanshu02 AT gmail.com
Arpit Jain, arpit.305 AT gmail.com
Abhinav Kumar, abhinavkumar516 AT gmail.com
Sourabh Mangal, mangal.sourabh13 AT gmail.com
Himanshu Panwar, hpanwar35 AT gmail.com
Happy Mittal, happy2332 AT gmail.com
Yashoteja Prabhu, yashoteja.prabhu AT gmail.com
Neeraj Kishore, mcs122804 AT cse.iitd.ac.in
Ankit Anand, ankit.s.anand AT gmail.com

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 NLP; intro to information retrieval; submodularity; current research trends.

Schedule

Start End Topics & Lecture Notes Readings Additional Resources
Jan 3 Jan 8 Introduction AIMA Chapter 1
Applications of AI
Jan 10 Jan 15 Uninformed search AIMA Chapter 3.1-3.4
Beam Search
Intuition of Search Algorithms
Search Algorithms Performance
Jan 17 Jan 21 Informed search AIMA Chapter 3.5-3.7
IDA*
A*/IDA* Example
Pattern Databases
Jan 22 Feb 5 Programming Assignment 1
Starter Code
Benchmark Problems
Jan 22 Jan 24 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)
Jan 28 Jan 31 Adversarial search AIMA Chapter 5
How Intelligent is Deep Blue?
Minimax Applet
Jan 31 Feb 5 Constraint Satisfaction AIMA Chapter 6 (skip 6.3.3)
Conversion to Binary CSP
NumberJack
Constraint Programming
Feb 6 Feb 24 Programming Assignment 2
Starter Code
Web Server Instructions
Feb 11 Feb 12 Logic and Satisfiability AIMA Chapter 7, 8.1-8.3
CSP vs. SAT
Feb 14 Feb 18 Advanced Satisfiability Advanced SAT Solvers (Sections 2.3, 2.4)
Phase Transitions
Backdoors
Feb 19 Feb 25 Classical Planning AIMA Chapter 10
FF Planner
Feb 20 Mar 13 Programming Assignment 3
Starter Code
MiniSat
Feb 26 Feb 26 Agent Architectures AIMA Chapter 2

Mar 11 Mar 12 Decision Theory AIMA Chapter 16.1-16.3, 16.6

Mar 12 Mar 18 Markov Decision Processes AIMA Chapter 17.1-17.4
MDP Survey (3.1-3.5, 4.1-4.3.1)

Mar 26 Mar 28 Reinforcement Learning AIMA Chapter 21.1-21.3
TD Learning for Backgammon
Convergence of Q learning
Mar 28 Apr 11 Programming Assignment 4
Code
Apr 1 Apr 2 Bandits and Monte Carlo Tree Search Monte Carlo Planning (Sections 3.1-3.3)
AIMA Chapter 21.4
UCT for Go
Monte Carlo Planning
Apr 4 Apr 25 Programming Assignment 5 (updated Apr 22)
Code (updated April 22)
Apr 4 Apr 4 Intro to Probability AIMA Chapter 13
History of Bayes Theorem
Apr 4 Apr 11 Bayesian Networks Representation AIMA Chapter 14.1-14.4
Influence Flow in Bayes Nets
Apr 15 Apr 16 Bayesian Networks Inference and Learning AIMA Chapter 14.5, 20
Log Probabilities
Apr 18
Apr 18
Intro to NLP
Future of Web Search,
IBM Watson Deep QA
Apr 22
Apr 25
Machine Learning Intro and Algorithms AIMA Chapter 18.1-18.4, 18.6-18.6.3,
18.7-18.7.3, 18.8-18.8.1, 18.9


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 (mostly programming) assignments due approximately every two weeks. One assignment may be in two parts.

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.