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

On Thu, Apr 21, 2016 at 1:20 PM, "Ingo Althöfer" <3-hirn-ver...@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

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

-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

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

Hi Erik, >> 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

Re: [Computer-go] Is Go group pattern recognition by CNN possible?

Petr, Tysvm! I really appreciate that. Jim On Thu, Apr 21, 2016 at 4:41 AM, Josef Moudrik wrote: > Thank you! > > Dne čt 21. 4. 2016 11:17 uživatel Petr Baudis napsal: > >> Hi! >> >> Since "the record's stuck", I have found this as another rant

Re: [Computer-go] Is Go group pattern recognition by CNN possible?

Thank you! Dne čt 21. 4. 2016 11:17 uživatel Petr Baudis napsal: > Hi! > > Since "the record's stuck", I have found this as another rant without > point, and djhbrown hasn't responded to my private request for staying > on topic and friendly, I have taken the liberty to "cast

Re: [Computer-go] Is Go group pattern recognition by CNN possible?

Hi! Since "the record's stuck", I have found this as another rant without point, and djhbrown hasn't responded to my private request for staying on topic and friendly, I have taken the liberty to "cast the first stone" and enabled the moderation bit for djhbrown. I'll be happy to

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

Likely it is almost impossible for neural nets of "moderate" size to identify life/death stati of a groups. One difficult example (in the spirit of old Minsky/Papert who asked perceptrons to identify the connectivity status of a "picture") might be the following X-"around the board"-group which