CSCI-431: Artificial Intelligence

This course provides an introduction to artificial intelligence. Topics include uninformed and informed (heuristic) search, adversarial search, reinforcement learning, Bayesian networks, Hidden Markov Models, machine learning algorithms, computer vision, natural language processing, and robotics. The course will include approximately four substantial programming assignments in Python. Co-requisite: CSCI 361 (Algorithms and Data Structures).

Contact Info

Instructor:	David Akers
Lectures:	Tu-Th 11:00-12:20 (TH 387)
Labs:	Some Thursdays, class will be held in TH409 or TH420
Phone:	879-3126
Email:	dakers@pugetsound.edu
Office:	Thompson 600
Office Hours:	Mon 3:00-3:50, Tues-Thurs-Fri: 2:00-2:50, and by appt.

• 12/22/11: The first day of class will be Tuesday, January 17, 2012.

Resources:

• Course syllabus: Handouts/csci_431_syllabus_spring_2012.pdf

• Textbook: Russell and Norvig, Artificial Intelligence: A Modern Approach (Third Edition), Prentice Hall.
• Planning to write code at home? See the CS 431 software installation guide.
• Python 2.6 documentation:
  • Official tutorial
  • Language reference
  • Quick reference
  
  
• Java to Python transition guide (somewhat useful but incomplete, and has quite a few typos)

Schedule:

Week	Topic	Reading	Quiz?	Asmt Out	Due
1/16	Introduction to AI, python 01-intro	Chapter 1		Python Tutorial	Friday 1/27
1/23	Agents and search 02-search1	Ch. 3.1-3.6		P01 (Search)	Monday 2/13 (checkpoint: Monday 2/6)
1/30	Heuristic-based search 03-search2 04-search3	Review sections 3.4-3.6
2/6	Constraint satisfaction problems 05-csp1 06-csp2	Ch. 6.1-6.5
2/13	Adversarial search (search for games) 07-adversarial1 08-adversarial2	Ch. 5.2-5.5	Quiz Thursday 2/16 on CSPs (practice problems)	P02 (Multi-Agent)	Wednesday 2/29 (last possible day to hand in: Monday 3/5)
2/20	Expectimax search, Markov Decision Processes (MDPs) 09-expectimax 10-mdp1	Sutton and Barto Ch. 3-4
2/27	MDPs, Reinforcement learning 11-mdp2 12-reinforcement1	Ch. 17.1-17.3		P03 (Reinforcement Learning)	Thursday 3/29 (last possible day to hand in: Tuesday 4/3)
3/5	Reinforcement learning, cont'd 13-reinforcement2 14-reinforcement3	Sutton and Barto Ch. 6.1, Ch. 2, Ch. 5	Quiz Tuesday 3/6 on MDPs (practice problems)
3/12	Spring Break
3/19	Probability, Bayes Nets: representation and independence 15-probability 16-bayesnets1	Ch. 13.1-13.5, Ch. 14.1-14.2
3/26	Bayes Nets: inference and sampling 17-bayesnets2 18-markov1 Bayes' Nets software	Ch. 14.4.1, Ch. 14.5.1	Quiz Tuesday 3/27 on probability (practice problems) (quiz solutions)	P04 (Ghostbusters)	Sunday 4/22 (last possible day to hand in: Wednesday 4/25)
4/2	Hidden Markov Models (HMMs) 19-markov2	Ch. 15.1-15.3, Ch. 15.5	Quiz Tuesday 4/3 on Bayes Nets/Markov Models (practice problems)
4/9	Machine learning (naive bayes, perceptron model) 20-particlefiltering 21-naivebayes	Review Ch. 15.5
4/16	Machine learning, cont'd 22-perceptrons 23-advanced1	No new reading
4/23	Computer vision, natural language processing, robotics 24-advanced2 Take-home exam out Thursday, due Monday at 5:00 pm link to exam	No new reading	No quiz
4/30	Final thoughts Last day is Tuesday.	No new reading
5/7	Final exam week There is no in-class final exam for this class.