Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Hi, Winrate of your pure CNN againts pachi retsugen is: GAMES WINRATE S.D.PAIRING 224 0.558 0.033 19-7.5-1-pachi-=1-detlef_54 221 0.407 0.033 19-7.5-1-pachi-=2-detlef_54 I used the https://github.com/jmoudrik/deep-go-wrap for the player. Regards, Josef On Tue, Dec 29,

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hi, I am fighting with the problem most seem to have with the strong move predictions at the moment, MCTS is not increasing the players a lot :) I wonder, if somebody measured the performance of the pure CNN54 against pachi 10k (or 100k), to get a

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Thank you for the feedback, everyone. Regarding the CPU-GPU roundtrips, I'm wondering whether it'd be possible to recursively apply the output matrix to the prior input matrix to update board positions within the GPU and without any actual (possibly CPU-based) evaluation until all branches come

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

I doubt that the illegal moves would fall away since every professional would retake the ko... if it was legal On 2015-12-09 4:59, Michael Markefka wrote: Thank you for the feedback, everyone. Regarding the CPU-GPU roundtrips, I'm wondering whether it'd be possible to recursively apply the

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

I think ko moves are taken into account on one of in the input planes for most configurations. At least I hope remember that correctly. Could it be achieved to create such a plane from the prior input matrix and following output matrix by difference? On Wed, Dec 9, 2015 at 2:08 PM, Igor Polyakov

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Hi! In case someone is looking for a starting point to actually implement Go rules etc. on GPU, you may find useful: https://www.mail-archive.com/computer-go@computer-go.org/msg12485.html I wonder if you can easily integrate caffe GPU kernels in another GPU kernel like this? But

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Regarding full CNN playouts, I think that problem is that a playout is a long serial process, given 200-300 moves a game. You need to construct planes and transfer them to GPU for each move and read result back (at least with current CNN implementations afaik), so my guess would be that such

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Hello Detlef, I've got a question regarding CNN-based Go engines I couldn't find anything about on this list. As I've been following your posts here, I thought you might be the right person to ask. Have you ever tried using the CNN for complete playouts? I know that CNNs have been tried for move

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Hi! Well, for this to be practical the entire playout would have to be executed on the GPU, with no round-trips to the CPU. That's what my email was aimed at. On Tue, Dec 08, 2015 at 04:37:05PM +, Josef Moudrik wrote: > Regarding full CNN playouts, I think that problem is that a playout

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Yes, that's why I wrote with current CNN implementations. But I still wonder whether my estimate for the round-trip length is at least of the correct magnitude. Josef On Tue, Dec 8, 2015 at 6:03 PM Petr Baudis wrote: > Hi! > > Well, for this to be practical the entire playout

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

I don't think the CPU-GPU communication is what's going to kill this idea. The latency in actually computing the feed-forward pass of the CNN is going to be in the order of 0.1 seconds (I am guessing here), which means finishing the first playout will take many seconds. So perhaps it would be

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Did everyone forget the fact that stronger playouts don't necessarily lead to an better evaluation function? (Yes, that what playouts essential are, a dynamic evaluation function.) This is even under the assumption that we can reach the same number of playouts per move. > On 08 Dec 2015, at

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

Of course whether these "neuro-playouts" are any better than the heavy playouts currently being used by strong programs is an empirical question. But I would love to see it answered... On Tue, Dec 8, 2015 at 1:31 PM, David Ongaro wrote: > Did everyone forget the fact

Re: [Computer-go] CNN with 54% prediction on KGS 6d+ data

As NNs basically learn the frequency of each move, using the value as its probability to be chosen in a simulation could be ok. Hideki David Ongaro: <6c2ff906-2a00-45c1-b892-2b14bef35...@hamburg.de>: >Did everyone forget the fact that stronger playouts don't necessarily lead to >an better