Author: Simon Read
Date: 04:10:28 02/26/98
Go up one level in this thread
On February 25, 1998 at 22:30:01, Fernando Villegas wrote: > Knowledge means something only if means what you call human > knowledge. And certainly so it is in chess programing. Code lines are > done for mimicking human knowledge. Surely there are some programs which try to extract knowlege of their own by adjusting their parameters so as to maximise their playing ability? Arthur Samuel did this with his checkers program, eventually using a non-linear model. This isn't human knowlege, because the computer got it simply by using the rules of the game. > That's why most of chess programming has something very similar to > alchemist practice, an issue of mixing things and then to see what > happens. There is a lot of that in manually adjusting parameters. Simon
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.