Re: [gnugo-devel] Research

[Gunnar Farnebäck]

Reona wrote:
>  I am a Junior at Princeton University looking for a research topic
>  on machine learning and Go. I was reading the task list posted on
>  the GNUgo and found this to be intersting.  
> 
> "Fuseki tuning by hand is difficult. People who are interested
>    in doing machine learning experiments with GNU Go could try
>    working with fuseki. This may be one of the areas with most
>    potential for substantial and reasonably quick improvements."
> 
> What kind of research has been done,

For publications about computer go you can check this bibliography:
http://www.markus-enzenberger.de/compgo_biblio/compgo_biblio.html

> and what kind of research do you think will be helpful in furthering
> computer go?

If you can find any machine learning approach that gives a
substantially stronger fuseki than what's currently in GNU Go, I think
a lot of people would be interested. We would certainly be at least.
:-)

/Gunnar