Re: computer-go: Machine Learning and Go

[Konstantin <konst@xxxxxxxxxxxxxxxx>]

On Wed, 31 May 2000, Johan Roos (QCS) wrote:

> As I understand it from Markus Enzenberger's description, I havnt read Thore's but
> it seems to be similar
> 
> xxxxxxx
> xoooo.x
> xxxxxxx
> 
> will have the same representation as
> 
> xxxx
> xo.x
> xxxx
> 
> is this right? 
> 
> If so the some concept(feature) of dead shape should be accounted for.
> 
> /Johan
> 

Yes you are right. If one ignores the surrounding liberties, the two
groups will have the same representation.
As I mentioned in one of my earlier posts, this method has some
drawbacks when it comes to seki and nakade.


/K