Author: Dann Corbit
Date: 08:59:21 08/04/99
Go up one level in this thread
On August 04, 1999 at 11:53:34, Helcio Alexandre Pacheco wrote: >Some days ago I read an article posted here about algoritms for perfect endgame >play. >If I remember well, there is only one for the KP-K endgame. I was wondering if >with the use of Neural Network, Fuzzy Logic or Genetic Algorithms, would be >possible to make a program to play for example KPP-KP endgame with perfection as >we already have a perfect player to teach the program. >It's a thought I had and I would like to know your opinion as I might work on >this if i see it worth such a work. I doubt it. Neural programs seem to have no temporal reasoning. I have one on my ftp site you can play with if you like. Even if it learns from thousands of excellent games, it still does very strange things from time to time.
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.