At the blackboard University of Washington Computer Science & Engineering
 CSE 473: Artificial Intelligence I
  CSE Home   About Us    Search    Contact Info 

 Home
 Schedule
 Assignments
 Team Info
 Abalone Tournament

 Mail archiveCSE only
 Anonymous feedbackCSE only
   

Objectives

This class will provide an introduction to Artificial Intelligence, explaining the challenges inherent in building an "intelligent system" and describing the main techniques and tools. We will focus on search, constraint satisfaction, knowledge representation, planning, machine learning, and reasoning about uncertainty. After taking the class you will know how to use machine learning to build a spam filter, build a simple expert system using Bayesian reasoning, and build a powerful game-playing program.

Administrivia

Class schedule: M, W, F 9:30-10:20, room EE1 037
Final exam: Wednesday, June 9, 8:30-10:20

Instructor: Dan Weld (weld at cs)
Office hours: Fridays 11-noon (CSE 588) but please feel free to email me for another time.

TA: Krzysztof Gajos (kgajos at cs)
Office hours: Thursdays 2:30-3:30 (CSE 218)

TA: Tessa MacDuff (tessa at cs)
Office hours: W 10:30-11:30 (CSE Atrium)

CSE473 Mailing List: Please subscribe to the class mailing list.

Textbook: The (required) textbook is Russell & Norvig "AI a Modern Approach," (Prentice Hall) 2nd edition, 2003. (Note: this book is much improved over the previous edition). We may also assign readings off the WWW.

Grading: Your final grade will be assigned based on the following (tentative weighting):

  • 45% homeworks (most will involve a significant programming component)
  • 15% midterm
  • 30% final
  • 10% class participation, extra credit, etc.

Late Policy: Unless otherwise indicated, assignments and projects are due by the start of lecture on their due date. If you hand in an assignment more than one hour late, we will take off 20% for each day (or portion thereof) that it is late. So, if an assignment is due on April 16, it must be in the TA or lecturer's hands by 9:30am (start of class) on that day, with a one hour grace period after that. In addition, we will waive one days worth of late penalties over the courseof the quarter. At quarters end, we will not give Incompletes as grades.

Cheating Vs. Collaborating 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.


CSE logo Computer Science & Engineering
University of Washington
Box 352350
Seattle, WA  98195-2350
(206) 543-1695 voice, (206) 543-2969 FAX
[comments to Krzysztof Gajos]