Re: [computer-go] Purpose of Neural-Nets?

[matth1@xxxxxxxxxxxxxx]

I have played around with neural nets for Go many years ago. I did not get very far, Go is vastly too complex to be attacked by a single net of any reasonable size. I am now working on developing CA analysis methods for mining Go positions so that a set of neural nets would have a more practical data set as input. After experience in other games, I am a firm believer in training nets using genetic rather than propagation algorithms. Anyone else have experience in this can comment?

Matt

happy new year everyone

>  from:    chrilly <chrilly@xxxxxxxxxxxxxxxxx>
>  date:    Tue, 30 Dec 2003 08:31:50
>  to:      computer-go@xxxxxxxxxxxxxxxxx
>  subject: Re: [computer-go] Purpose of Neural-Nets?
> 
> Dear all,
> 
> In my own field, computer-chess, there are no real efforts to build a neural-net programm. In Go neural nets seem to be an inportant concept. Can the neural-net experts explain me the purpose? Is it primarly:
> a) To make the strongest Go-programm possible.
> b) To learn network-learning.
> c) To write a paper about network-learning.
> d) Its just fun to play around with neural-networks.
> e) Others.
> 
> In case of a). One could first learn the weights and then hardcode the weight-function to speed up the evaluation. Alternatively one could have 2 versions of a program. The slow learner and the fast tournament-player. Is this done, or is a neural-net programm always a neural-net program?
> 
> Best Regards
> Chrilly
> 

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