Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: chess and neural networks

Author: Ingo Lindam

Date: 04:29:16 07/02/03

Go up one level in this thread


On July 02, 2003 at 04:17:28, Rolf Tueschen wrote:

>On July 01, 2003 at 18:20:12, Fernando Alonso wrote:
>
>>On July 01, 2003 at 15:46:06, Ralph Stoesser wrote:
>>
>>>Right, that's what I intend with my question. During a 'normal' chess game a
>>>chess engine has to face often positions where the difference in evaluation
>>>between let's say the 5 best moves or so is very small. In such circumstances a
>>>trained neural network maybe could help to find good positional moves better
>>>than a classical evaluation.
>>>
>>>Ralph
>>
>>I agree with you, that is the important point. To put it in other words, can I (
>>a patzer) with my little chessknowledge, beat Fritz 8 using Fritz 8 to analyze
>>the moves I my brain "thinks"?. I am sure there is a level of playing were
>>someone using a program can beat easily the same program playing alone. But can
>>that knowledge be implemented in neural networks?
>
>
>What knowledge? For the moment nobody addressed Tom's objection IMO. Chess is
>very concrete.
>
>Now what you all are saying that there existed a "knowledge" to find "good"
>positional moves. Of course our human GM have that knowledge. It is a mixture
>out of the evaluation of the very concrete position, deeper (later) consequences
>and again very concrete calculations for these _later_ positions. I dont see why
>"fuzzy" approaches should do that job better than the "classical" evaluation.
>
>What you in special are proposing is NOT a question of "knowledge" but simply
>one of cheating. You know exactly the "thought process" of a program. So you can
>always discover a difference in the evaluation of the final position. Now the
>trick is to invite the machine to go blindly for a big difference which is then
>the win for you. This is typically the approach of smart amateurs with weaker
>chess talents. [Dreihirn comes to mind.] But real chess is something else. A GM
>does NOT win because he's a clairvoyant but because his judgement (combining the
>very concrete with the general experience for the actual and then later
>positions) is "better". A weaker chessplayer has no adaequate judgement at all.
>I cant see why neural networks should have one - where should it come from? Out
>of the blue?
>
>Again, you simply didn't address Tom's objection that "sometimes" it is very
>important where your Rook is standing. Very concrete. How to handle that
>"sometimes" it is "important"?
>
>Rolf

I (as well as Rolf) ) don't expect the wished improvement by putting a neural
network or another chess knowledge using "judge" onto the results of a e.g.
Fritz 8 search.

And ofcourse chess is very concrete and "sometimes" it makes a big difference
whether to rook is on e1 or d1. It should be part of chess knowledge or "general
experince" to distingish between the useful and the unnecessary information or
features of a postion within a very concrete evaluation process.

I could imagine a neural network to learn some chess knowledge or "general
experience". Although a neural network would not be my first choice.

I am sure there is a lot of less concrete chess knowledge a program coulöd use
in search and/or evaluation process and a GM is using withing his evaluation.
This knowledge should lead to aims and plans. A plus in the evaluation means
nothing without an idea (of a way)/ a plan / a possible sequence of
transpositions towards the aim.

And also to know what you know makes you able to find a (working) plan. So if
you don't know anything about rook endings or you know you can't play them
accurate you should not transpose to one if there is another way towards the
aim. Or if you/the programm has all the experience of all relevant games of
chess history it should not transpose to the endings that never have won before,
but to the endings with a simple winning plan even though when the material plus
will decrease or you have to give away one of three "positional advantages".

Internette Gruesse,
Ingo



This page took 0.02 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.