[Computer-go] Recursive Neural Networks

Petr Baudis pasky at ucw.cz
Thu Jan 24 06:29:37 PST 2013


On Wed, Jan 23, 2013 at 04:41:57PM -0500, George Dahl wrote:
> This paper reports 36% move prediction accuracy:
> http://www.cs.utoronto.ca/~ilya/pubs/2008/go_paper.pdf

C.f. also http://research.microsoft.com/apps/pubs/default.aspx?id=67955
which reports 34% accuracy for top move, 66% accuracy for top five moves
suggested.

I'm not sure if anyone measured Remi Coulom's pattern model performance
in move prediction.

P.S.: As already mentioned, it should go without saying that there is
very little correlation if any between move prediction rate and playing
strength as a sole move generator or a feature provider.

				Petr "Pasky" Baudis



More information about the Computer-go mailing list