[Computer-go] Neural Net move prediction

Marc Landgraf mahrgell87 at gmail.com
Thu Feb 4 03:52:39 PST 2016


lately a friend and me wondered about the following idea.

Let's assume you have a reasonably strong move prediction DCNN. What
happens if you now train a second net on the same database.
When training the first net, you tried to maximize the judgement value
of the expert move. But for the second net you now try to maximize the
maximum of the judgement of both nets. This means, that the second net
does not profit from finding moves the first net can easily find, but
instead will try to fill in the weaknesses of the first net.
In practical application the easy static usage would be to first
expand the top2 candidates of the first net, then mix in the top
candidate of the second net, then again the next 2 candidates from the
first net, etc.

What do you guys think about that?

Cheers, Marc

More information about the Computer-go mailing list