Author: Pete R.
Date: 16:24:38 07/25/00
Go up one level in this thread
On July 25, 2000 at 10:51:14, Albert Silver wrote: >I'd love to here what the programmers think. I already know how a few members >will follow up... :-) > > Albert Silver > >http://www.nytimes.com/library/national/science/072500sci-artificial->intelligence.html According to an article about the DB match (linked elsewhere on this board), "Now that the match is over, a few pieces of information about Deep Blue's preparations are beginning to emerge. Besides Grandmaster Joel Benjamin, Deep Blue was tested by several New York-based grandmasters as well as Spanish Grandmaster Miguel Illescas. Other researchers at IBM's T.J. Watson facility were apparently brought into the project. ** For example, Gerry Tesauro, best known for his program TD-Gammon (playing at a level on par with the best backgammon players), used his neural net technology to help tune Deep Blue's evaluation function. ** The biggest strides forward seemed to be in the evaluation function, where extensive efforts were spent trying to improve the program's play in positions where computers have a reputation for playing weakly in. As far as we can tell from a small sample of six games, the Deep Blue team have made significant strides here." ** emphasis added. In principle I didn't see any reason why the evolutionary neural net approach wouldn't work for evaluation tuning, and according to this article this approach had been used to some extent for DB.
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.