[Computer-go] Is Go group status recognition by CNN possible?

Detlef Schmicker ds2 at physik.de
Thu Apr 21 05:47:00 PDT 2016


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

You are right, usually they do quite well, but e.g. liberty races with
large dragons are quite difficult.

And there must be a reason, why the value net was so wrong in the game
alphgo lost:)



Am 21.04.2016 um 13:51 schrieb Erik van der Werf:
> On Thu, Apr 21, 2016 at 1:20 PM, "Ingo Althöfer"
> <3-Hirn-Verlag at gmx.de> wrote:
> 
>> Likely it is almost impossible for neural nets of "moderate"
>> size to identify life/death stati of a groups.
>> 
> 
> No. Neural nets (even shallow ones like we used over a decade ago)
> are quite capable to identify life/death. Sure you can construct
> pathological examples that in theory require some form of
> recursion, but in practice this now seems to be mostly a
> non-issue.
> 
> 
> 
> _______________________________________________ Computer-go mailing
> list Computer-go at computer-go.org 
> http://computer-go.org/mailman/listinfo/computer-go
> 
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.22 (GNU/Linux)
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=0ZrL
-----END PGP SIGNATURE-----



More information about the Computer-go mailing list