Re: computer-go: Learning from existing games

[Daniel Bump <bump@xxxxxxxxxxxxxxxxxx>]

> with about 1e5 weights, it can achieve > 45% wins against GnuGo.
> The input has higher level features than the early versions, but still 
> relatively simple ones compared to other Go programs.
> Mostly the increase in playing strength come from a sophisticated 
> network architecture. There is a diagram shown in these slides:
> http://www.cs.ualberta.ca/~emarkus/nngo/nngo-2up.ps

How about posting a Neurogo game or two so we can see what 
it's style is like these days?

Dan