Re: computer-go: Machine Learning and Go

[Konstantin <konst@xxxxxxxxxxxxxxxx>]

On Wed, 31 May 2000, Serge Boisse wrote:
> consider the  beginning of the game, with, say, just 2 stones (one of each
> color) on the board. We know that the rest of the game will be very different if
> the first (black) stone is for instance at 4-4, 3-4, 3-5 or 4-5 point. The white
> response might also be put at the oposite diagonal corner, or at an adjacent
> corner, and the remaining game will again be very different. All of these have
> same CFG, however :
> 
> 	w---.---b
> 

As I understood it, emtpy intersections are not contracted, so placing
the two stones in different positions will produce different CFGs.

/K