CSEP 573 - Applications of Artificial Intelligence

Instructor: Mausam
(mausam at cs dot washington dot edu)
Office hours: by appointment, CSE 454

TA: David Broderick
(dbroder at cs dot washington dot edu)
Office hours:Wednesdays 5-6 PM, CSE 220

Schedule

Week	Dates	Topics & Lecture Notes	Readings	Resources and Advanced Readings
1	Jan. 5	Introduction, Uninformed Search, Informed Search.	AIMA Chapters 1,3 (Extra reading: Ch. 2, Beam Search)	Video Anytime A* Dynamic A*
2	Jan. 12	Local Search, Adversarial Search, Computational Voting Theory.	AIMA 4.1-4.2, 5.1-5.4, 5.7-5.9, 6 (Extra reading: 5.5, 5.6)	How Intelligent is Deep Blue? General Game Playing
3	Jan. 19	Constraint Satisfaction, Logic and Satisfiability.	AIMA 6, 7, 8.1-8.3 (Extra reading: Ch. 9)	Constraint Programming
4	Jan. 26	Classical Planning, Agents, Decision Theory	AIMA 10, 2, 16.1-16.3, 16.6	FF Planner Self-driving cars
5	Feb. 2	Markov Decision Processes, Probability Basics, Bayesian Networks	AIMA 17.1-17.4, 13, 14.1-14.4	Monte Carlo Planning
6	Feb. 9	Bayesian Networks Approximate Inference and Learning, Intro to NLP	AIMA 14.5, 20.1-20.3	Future of Web Search, IBM Watson Deep QA
7	Feb. 16	Guest Lecture: Applications of Modern SAT Solvers (Ashish Sabharwal, IBM Research) Hidden Markov Models, Intro to Learning,	AIMA 15.1-15.3, 18.1-18.2, 22.2 (Extra reading: 15.5, 15.4)
8	Feb. 23	Guest Lecture: Learning to Make Music (Sumit Basu, Microsoft Research) Text Categorization using Naive Bayes	AIMA 18.3,18.6-18.8
9	March 2	Guest Lecture: Machine Learning Applications in Industry (Joseph Sirosh, Amazon) Decision Trees, Neural Networks, Nearest Neighbor	AIMA 18.10-18.11
10	March 9	Guest Lecture: Building Machines for Care: Sensors, Algorithms and Interfaces to Support Behavior-Based Caregiving (Matthai Philipose, Intel Research) Ensemble Learning, Unsupervised Learning, Semi-supervised Learning, Wrap-up.	TBA	Dawn of AI

Textbook

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

Grading

Assignments: 60%; Class Participation: 10%; Final: 30%

There will be four assignments:

Assignment 1: assigned Jan 5th, due Jan 19th 6:30 pm, Description, Starter Code Drop Box
Assignment 2: assigned Jan 19th, due Feb 2nd 6:30 pm, Description: (as pdf), (as xml).
Assignment 3: assigned Feb. 2nd, due Feb. 16th Description: (as pdf), (as xml).
Assignment 4: assigned week 7, due week 10 Description: (as pdf), (as xml).

The gradebook can be found here.

Course Administration and Policies

Check the class discussion board for ongoing updates
Subscribe to the course mailing list.
Assignments will be done individually unless otherwise specified. You may discuss the subject matter with other students in the class, but all final answers must be your own work. You are expected to maintain the utmost level of academic integrity in the course.
Assignments may be handed in up to a week late, at a penalty of 10% of the maximum grade per day.
Comments can be sent to the instructor or TA using this anonymous feedback form

Cheating Vs. Collaborating Guidelines

As referenced 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 risk losing your position as a student in the department and the college. The department's policy on cheating is to report any cases to the college cheating 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 University guidelines.

The Gilligan's Island Rule: This rule says that you are free to meet with fellow students(s) and discuss assignments with them. Writing on a board or shared piece of paper is acceptable during the meeting; however, you should not take any written (electronic or otherwise) record away from the meeting. This applies when the assignment is supposed to be an individual effort or whenever two teams discuss common problems they are each encountering (inter-group collaboration). After the meeting, engage in a half hour of mind-numbing activity (like watching an episode of Gilligan's Island), before starting to work on the assignment. This will assure that you are able to reconstruct what you learned from the meeting, by yourself, using your own brain.

The Freedom of Information Rule: To assure that all collaboration is on the level, you must always write the name(s) of your collaborators on your assignment. This applies when two groups collaborate.