Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Knowledge is not elegant.

Author: Thorsten Czub

Date: 11:31:14 06/14/98

Go up one level in this thread


On June 14, 1998 at 13:50:19, Don Dailey wrote:

>I think a knowledge based approach to computer chess is not elegant at
>all.  However I use  it because I  do not see a  better  approach.

Good !
I like this Don !


> My
>program  keeps accumulating more and more  knowledge and seems to keep
>improving as a result of it.

Thats good.


> I'm forced to  use this ugly brute force
>technique because I do not know a better way.

:-)

Nobody knows how to do...
But with trying different ways, evolution will show...


>At the  rate we are going with  ram prices plummeting and our computer
>memories getting larger and larger, we may someday have as much memory
>in our  computers  as  humans have in   their  heads.

Having the memory is not a question of quantity. IF you computers would
have all the memory of a human brain, they would have the problem to
understand which knowledge is important in which situations. The human
brain is very good in knowing WHICH knowledge to use when.

>   Already  chess
>programs use many megabytes  of memory, and if  we continue  this ugly
>trend toward modeling the human brain

:-))

ugly trend toward modeling the humain brain :-)))


>we will soon have chess programs
>requiring huge amounts of memory.  This is not a pleasing development
>at all and is so wasteful.

You must teach the program to forget the unimportant stuff. Than the
"brain"=computer-memory will find out by itself which knowledge when to
use.
Let your computer sleep about the data, like a human beeing does.
Sleep is our biggest weapon against too much data.
You put your book under the pillow and sleep, after drinking a glass of
milk.
And the next day you will be able to differenciate between important and
unimportant stuff. Very nice way, isn't it ? I don't see that our
machines work this way. Anybody tries to quantify the data and the
knowledge. Nobody tries to qualify it, with "forgetting" e.g.

>The culmination of all  of this might  be the  32 man database.   This
>will be a sad day   indeed when a  simple table  lookup gives you  the
>right  answer  in every position.   Then  our  programs will play like
>super humans, having instant and perfect intuition in every position.

We will change to GO than ! :-)) Or try with loving girls instead,
i guess it will take more time for the materialists to create a
girl-database too :-))

>- Don



This page took 0.06 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.