Author: Janosch Zwerensky
Date: 02:29:45 02/19/04
Go up one level in this thread
>i don't know about this. it's fairly clear that the brain does extensive pattern >recognition to select a small number of candidate moves instead of looking at >all moves. insofar i think the difference between computer and human chess is >quite well understood. however, it's rather unclear to me that porting this type >of chess-playing to a computer is the right way to go because >1) you need lots of processing power for the pattern recognition >2) any selective search is prone to errors when it's candidate move selection >misses an important move. (1) might not matter much in the long run if the human way of doing things turned out to behave better asymptotically. I think one could argue that this ideed is the case, because relative to computers humans *do* apparently get stronger when you increase thinking time. Of course, this argument at best will help to defend a hybrid approach, since also in correspondence chess and even theoretical openings analysis human-computer teams do seem to dominate humans (but also computers) today. >(...) Regards, Janosch
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.