Re: computer-go: Neural Nets: suggesting and evaluating

[Arend Bayer <arend.bayer@xxxxxx>]

On Wed, 6 Aug 2003, Heikki Levanto wrote:

> I have often been wondering about using much higher level inputs to the
> NN. By doing a lot of tactical reading, it should be easy to get a good
> picture of which stones are connected (and how well), which are alive to
> some degree, and so on. Evaluating the position from such preprocessed
(...)

> Is this a well-known approach, or have I stumbled upon a new idea? Any
> experiences or even speculation on how it might work or fail?

Maybe I misunderstand s.th., but it seems to me that you can find a lot
of posts by Markus Enzenberger in the archives of this very mailing
list.

Arend