Path: utzoo!utgpu!news-server.csri.toronto.edu!rpi!usc!pollux.usc.edu!mamisra
From: mamisra@pollux.usc.edu (Manavendra Misra)
Newsgroups: comp.ai.neural-nets
Subject: Chip vs Chess Master
Keywords: Games, chess
Message-ID: <31403@usc>
Date: 27 Mar 91 22:58:39 GMT
Sender: news@usc
Distribution: comp
Lines: 20
Nntp-Posting-Host: pollux.usc.edu

Last night, I happened to see a Nova episode which talked about a match-up
between Gary Kasparov (the current Chess world champion) and Deep Thought
(AI software developed at CMU and IBM which is currently the best chess
playing program). Deep Thought essentially carries out a brute force search
of the game tree in deciding its moves. There was lots of discussion of the
standard "computers taking over the world" arguments during the program and
people with backgrounds ranging from CS to Chess GM's gave their opinions.
Quite a good program and much to the relief of most of the people gathered
for the match, Kasparov won it.

I was wondering if there was research going into developing "neural"
algorithms for playing games like Chess. I recall that there was some
work by A. L. Samuel in the 50's and 60's on a program for playing 
Checkers and that it was adaptive in some sense and it also drew from
a memory of stored games.

Also, I'd like to hear what others thought of the program.

Manav.