Author: Sune Fischer
Date: 06:22:58 02/17/04
Go up one level in this thread
>Yes, now. But think about how strong a computer might be if it could emulate >the human approach to chess. Pattern-recognition and extrapolation, at which >the brain can excel, are probably the best way to limit tree size (at least >better than what we do now). As computers get faster, with access to huge >memory, the standard minimax with alpha/beta approach will improve. But the >real breakthrough will occur when our primitive knowledge of brain function >becomes better understood, and we can take advantage of vast memory and >processing speed to replicate, and then improve upon, the human approach to >chess. I think people on this board in general underestimates the human brain. They consider the measly number of ~5 nodes a second and then claim computers are inefficient at chess. Reality is that the humans brain uses a billion neurons in parallel, the speed at which this thing processes patterns to a lifetime large database is amazing, it simply dwarfs Deep Blue into the ant stage. The only reason why computers stands a chance in chess is because the brain is not that good at tactical combinations. For that reason I don't believe the right approach to chess programming is to make computers play like a human, first of all it would simply require way too much computing power and secondly it would make it vulnerable to the same human pruning flaws. Perhaps when we get quantum computers we will finally have something that can compete with the human brain :) -S. >But at that point, will computers want to play chess? :) > >Will
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.