590AI Autumn '01
Artificial Intelligence Hit Parade
Greetings, and welcome to 590AI, Autumn 2001! The focus of this seminar
is slightly different this year - we'll be reading the Top Ten recent papers
in AI, as determined by a broad-based and statistically-sophisticated survey
covering the AI faculty in this department. If you're interested
in AI, be here or be...not well-rounded.
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: Wednesday 4:30 - 5:20
Meeting place: EE1
045
Organizer: Oren Etzioni
<etzioni@cs.washington.edu>
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, 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. The list of Hit Parade papers is below,
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. Please feel free
to form clusters and jointly present.
About cookies
Speaking of well-rounded: Each week's seminar will be catered by
one of the students in the class. The "Cookie 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 newstand 5 minutes before class time, 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
Debate and food fight how-to
-
Bring a single-slide's worth of proposal or comment, and a brief, provocative
description. Topics might include:
-
How might we progress toward the functional goals (the ideals) of the "Semantic
Web"?
-
What can AI contribute? Are there any AI problems here?
-
Expect to be allocated approximately 45/N minutes, where N = number of
people who show up with proposals. But you only get to talk for ~half
that time -- the other half, you get heckled.
-
Wear flame-proof, easily-cleaned attire.
List of papers
Hideki Asoh and Toshihiro Matsui, A
Unified Framework of Map Learning with a Hierarchy of Probabilistic Maps
Tim Berners-Lee, James Hendler, and Ora Lassila, The
Semantic Web
Henry Kautz, Cooperative Cognition
(Please see link sent to the course mailing list.)
Joel Kleinberg, Authoritative
Sources in a Hyperlinked Environment
Toshihiro Matsui, Hideki Asoh, John Fry, Youichi
Motomura, Futoshi Asano ,Takio Kurita, Isao Hara, and Nobuyuki Otsu, Integrated
Natural Spoken Dialogue System of Jijo-2 Mobile Robot for Office Services
Melanie Mitchell and Stephanie Forrest, Genetic
Algorithms and Artificial Life
Abstract: Genetic algorithms are computational models
of evolution that play a central role in many artificial-life models.
We review the history and current scope of research on genetic algorithms
in artificial life, using illustrative examples in which the genetic algorithm
is used to study how learning and evolution interact, and to model ecosystems,
immune system, cognitive systems, and social systems. We also outline
a number of open questions and future directions for genetic algorithms
in artificial-life research.
Peter Stone and Manuela Veloso, Task
Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication
for Real-Time Strategic Teamwork
Lapoon R. Tang and Raymond J. Mooney, Automated
Construction of Database Interfaces: Integrating Statistical and Relational
Learning for Semantic Parsing
Send corrections to
tressel@cs.washington.edu