Author: Landon Rabern
Date: 23:03:20 07/01/03
Go up one level in this thread
On July 01, 2003 at 15:50:19, Anthony Cozzie wrote: >On July 01, 2003 at 14:21:12, Tom Kerrigan wrote: > >>On July 01, 2003 at 13:32:19, Ralph Stoesser wrote: >> >>>Hello *, >>> >>>Why no top engine uses neural networks for positional evaluation in non-tactical >>>situations? Are there interesting publications about neural networks and chess >>>programming? >>> >>>Ralph >> >>Neural networks are for analyzing things that are >>"fuzzy"--voice/image/handwriting recognition, etc. Chess is a very exacting >>game. (It makes a big difference if your rook is on d1 vs. e1.) I doubt neural >>networks will ever be useful for chess. >> >>-Tom > >The human brain is also rather "fuzzy" and it seems to play chess rather well, >at least in some individuals :) Neural nets aren't used for chess because they >simply aren't as good as a human-developed evaluation function. Humans have >spent a lot of time trying to generate rules (to help other humans) that work >for chess, and it isn't too hard to teach those rules to computers. A neural >net would abandon all that, and start over from scratch, so to speak. > >Anthony I made an attempt to use a NN for determining extensions and reductions. It was evolved using a GA, kinda worked, but I ran out of time. to work on it at the end of school and don't have my computer anymore. The problem is that the NN is SLOW, even using x/(1+|x|) for activation instead of tanh(x). Regards, Landon
This page took 0.02 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.