[Computer-go] Teaching Deep Convolutional Neural Networks to Play Go

Stefan Kaitschick stefan.kaitschick at hamburg.de
Fri Dec 19 05:27:33 PST 2014


That's pretty good looking for a pure predictor. Considering it has no
specific knowledge about semeais, ladders, or ko threat situations...
Switching out the pattern matcher (not the whole move generator) in an
existing mc program, should be pretty straightforward. Even if the nn is a
lot slower than the orig. pattern matcher, it could still make sense high
up in the tree.
If this does prove fruitful, the question of what transforms of the raw
position should be fed to the nn could be the next big thing. After the
almost annoying success of general purpose mc, this would be a more poetic
line of research.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://computer-go.org/pipermail/computer-go/attachments/20141219/f4146d7d/attachment.html>


More information about the Computer-go mailing list