[Computer-go] global-pro-move-matching (was Recursive NeuralNetworks)
sheppardco at aol.com
Wed Jan 23 16:54:14 PST 2013
No one was using move prediction rates as a measure of strength.
From: computer-go-bounces at dvandva.org
[mailto:computer-go-bounces at dvandva.org] On Behalf Of Darren Cook
Sent: Wednesday, January 23, 2013 6:54 PM
To: computer-go at dvandva.org
Subject: Re: [Computer-go] global-pro-move-matching (was Recursive
> E.g., they report that the top-ranked move from their neural net has a
> 10% chance of matching a pro move on a 19x19 board....
> And if you use a large-scale pattern approach (e.g., Remi's work),
> then you can predict over 40% and maybe up to 50% of pro moves.
This is a poor measure of strength though (which is why most go programmers
concentrate on win-rates against Gnugo, or KGS ratings, etc.)
I chose 3,4 in top-right corner for my first move; the pro chose 4,4.
Mark it down as just as bad as choosing the 1,1 point.
I chose the hane-tsugi sente sequence at A10. The pro first played the
monkey jump sente sequence in the top-right then played A10. Mark my choice
as just as bad as poking my own eye out.
Computer-go mailing list
Computer-go at dvandva.org
More information about the Computer-go