590AI Autumn '00

Current Topics in Artificial Intelligence

Greetings, and welcome to 590AI, Autumn 2000! The focus of this seminar is "Current Topics in Artificial Intelligence", with a particular aim at AI research being done here at the UW. The schedule appears below and includes talks by invited guests, current grads discussing their research, and topics of interest to the AI group at large.

If you're interested in AI, then be sure to sign up for this seminar!

Administrivia

Like most all other classes in the department, CSE 590AI has a mailing list, managed by majordomo. Please sign up by sending a message to majordomo@cs.washington.edu with the text subscribe cse590ai in the body. You can view an archive of the mailing list online as well.

Meeting time: W 4:30 - 5:20
Meeting place: EE1 003

About credits

590AI is offered as a 1 - 3 credit course. Signing up for one credit is, of course, the minimum, and the minimum will be expected of you: attend the seminars, listen to the presentation, and participate in discussions. If you'd just like to get a feel for AI research here at the UW, then sign up for one credit of 590AI and enjoy the presentations.

If, on the other hand, you have an active interest in AI and would like to present during the quarter, then you should sign up for 3 credits of 590AI. We're asking folks to present either their current research work or a recent paper of common interest (a list of possible papers is below, but feel free to suggest a paper yourself). Don't worry, we're not asking for AAAI conference talks, here; we're more casual than that. What we're after is a talk that is accessible to folks who have read (or at least skimmed) the paper you're presenting, but who may not have read any other related work. If you're presenting your own work, it'd be great if you could include results / findings / whatever that has you excited about your work this week.

About cookies

590AI will subscribe to the same cookie philosophy as 590Q. Thus, each week's seminar will be catered by one of the students in the class. The "Cooking supplier" should bring enough treats (typically cookies, but feel free to be creative) for all. Fare from the past has ranged from Peppridge Farms cookies bought at the HUB newsstand, all the way to peanut brittle, brownies, and Kool-aid, all prepared by hand. If you're worried about being adequate, just don't follow Steve Wolfman.

The schedule

Wednesday Presentation Cookie supplier
9/27 Organizational meeting. AI faculty (Pedro, Oren, Dieter, Henry, Marina, and Dan) present an overview of their research. Corey Anderson
10/4 David Azari, presenting "Focused crawling: A new approach to topic-specific Web resource discovery" Pat Tressel
10/11 "Faster Solution of Encoded Planning Problems and Some Related Issues". Ronen Brafman, Ben-Gurion University Sarah Schwarm
10/18 AnHai Doan and Ana-Maria Popescu will present Enhanced hypertext categorization using hyperlinks. Julie Goldberg
10/25 Geoff Hulten will present "Efficient identification of Web communities" Molly Bostic
11/1 Deepak Verma will present "Learning to probabilistically identify authoritative documents" David Grimes
11/8 Guest speaker Nuria Oliver, from Microsoft Research, will present her work on intelligent interfaces. Take a peek at some of the papers she's coauthored: A Bayesian Computer Vision System for Modeling Human Interactions; Graphical Models for Driver Behavior Recognition in a SmartCar; .LAFTER: A Real-time Face and Lips Tracker with Facial Expression Recognition. Steve Wolfman
11/15 Sarah Schwarm will present "The Limits of Speech Recognition" by Ben Shneiderman and "Natural Spoken Dialogue Systems for Telephony Applications" by Susan J. Boyce, both in [CACM vol 43 no. 9, September 2000] Tessa Lau
11/22 Steve Wolfman will present his work on discoursive user interfaces [compressed]. Dan Weld
11/29 Corey Anderson will present his work on adaptive web sites. Adam Carlson
12/6 Molly Bostic will present Paek and Horvitz's paper "Conversation as Action Under Uncertainty". AnHai Doan

Possible presentation papers

As partial background, a very good survey to read is:
Send corrections to
corin@cs.washington.edu