Author: Christophe Theron
Date: 10:45:20 12/12/01
Go up one level in this thread
On December 12, 2001 at 12:10:32, Otello Gnaramori wrote:
>On December 12, 2001 at 11:34:09, Christophe Theron wrote:
>
>>
>>On the other hand there are heuristics the human players use that are of too
>>high level at this time for computers. I guess the concept of planning is one of
>>them. Human players are able to build on their past experience to come up in a
>>given position with a set of plans that are most likely applicable.
>
>That kind of human expertise is called "pattern recognition" , and was
>discovered by De Groot in the '50 testing human chess masters .
>
>It's based mainly on visual memory and I think that with an huge learning
>database (expert system, probably) of the middlegames you can arrange it...
>
>BTW an interesting link on the research in this field is as follows :
>http://www.psychology.nottingham.ac.uk/credit/projects/chess_expertise/main.html
>
>w.b.r.
>Otello
I know the researchs you are talking about, but nothing came out of it. I mean
that top level programs do not use this concept of pattern recognition at all.
That's why I say that it is the kind of heuristic that only human players use.
Christophe
This page took 0.01 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.