Re: [computer-go] Pattern matching - example play

[Heikki Levanto <heikki@xxxxxx>]

On Fri, Dec 03, 2004 at 10:27:58PM +0100, Vincent Diepeveen wrote:
> 
> >I would not completely write off higher-level planning and neural nets,
> >and other fancy theories. Many of them have shown their values in
> 
> We can have lengthy discussions, but the majority of ANN top researchers
> agree with me here that for game playing ANN is completely useless.

Well, as far as I know, neural nets work quite well for backgammon. I
admit it s a very different game, but shows that ANNS are not
*completely* useless for *game* *playing*. 

I agree with you, that if you just feed the board position into an ANN,
you can at best train it to recognize similar games, and you will not
anywhere. But there are other ways to use ANNs.

For example, if you feed it the number of groups, the number of their
liberites, and so on, it should be relatively easy for it to learn that
a position where groups are connected is a better one than a situation
with many small isolated groups. And if you feed it the results of some
influence calculations, it should easily learn that the one that has
most territory is often ahead. Both of these are easier to program in
hand, I admit. But the same ANN could also learn to balance these
separate considerations, and a few more, and come up witha  decent
evaluation function.

> Yet no one is stopping you believing in a black box that can solve the game
> without much calculation. A formula X based upon a few artificial neurons.

Of course I do not believe in a magic black box! But I believe that as
things are now, it is not yet sure which technique(s) are the best
suited for solving computer go. You advocate a deep global search, with
some good arguments, I give you that. I am still not convinced that it
is the only way, or even the best way to go. Sure it is worth studying,
but being as problematic as it is, I believe progress can be made in
other directions too. 


Best regards

  Heikki

-- 
Heikki Levanto   "In Murphy We Turst"     heikki (at) lsd (dot) dk

_______________________________________________
computer-go mailing list
computer-go@xxxxxxxxxxxxxxxxx
http://www.computer-go.org/mailman/listinfo/computer-go/