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

Darren Cook darren at dcook.org
Mon Dec 15 03:24:32 PST 2014


> When I had an opportunity to talk to Yann LeCun about a month ago, I asked
> him if anybody had used convolutional neural networks to play go and he
> wasn't aware of any efforts in that direction. 

There was work using neural networks in the mid 1990s, when I first
started with computer go. I think the problem, at that time, came down
to if you use just a few features it was terrible quality, but if you
used more interesting inputs the training times increased exponentially,
so much so that it became utterly impractical.

I suppose this might be another idea, like monte carlo, that just needed
enough computing power for it to become practical for go; it'll be
interesting to see how their attempts to scale it turn out. I've added
the paper in my Christmas Reading list :-)

Darren

>> Teaching Deep Convolutional Neural Networks to Play Go
>> http://arxiv.org/pdf/1412.3409v1.pdf
>>
>> Thier move prediction got 91% winrate against GNU Go and 14%
>> against Fuego in 19x19.




-- 
Darren Cook, Software Researcher/Developer
My new book: Data Push Apps with HTML5 SSE
Published by O'Reilly: (ask me for a discount code!)
  http://shop.oreilly.com/product/0636920030928.do
Also on Amazon and at all good booksellers!



More information about the Computer-go mailing list