To be honest, what I really want is for it to self-learn, like David Silver's TreeStrap did for chess, but on the one hand I guess I should start by reproducing the existent, and on the other hand if we need millions of moves to train the net, that's going to make for very slow self-play... Also, David Silver was associated with Aja Huang's paper, and I'm guessing therefore that it is very non-trivial to do, otherwise David Silver would have done it already :-) _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
- Re: [Computer-go] Teaching Deep Co... Stefan Kaitschick
- Re: [Computer-go] Teaching Dee... David Fotland
- [Computer-go] Teaching Deep Convolutional N... Ingo Althöfer
- Re: [Computer-go] Teaching Deep Convolutional Neural Net... Detlef Schmicker
- Re: [Computer-go] Teaching Deep Convolutional Neura... Petr Baudis
- Re: [Computer-go] Teaching Deep Convolutional N... Detlef Schmicker
- Re: [Computer-go] Teaching Deep Convolutional N... Hugh Perkins
- Re: [Computer-go] Teaching Deep Convolution... Hugh Perkins
- [Computer-go] Fwd: Teaching Deep Convol... Hugh Perkins
- [Computer-go] Fwd: Teaching Deep C... Hugh Perkins
- [Computer-go] Fwd: Teaching De... Hugh Perkins
- Re: [Computer-go] Fwd: Teachin... Michael Markefka
- Re: [Computer-go] Fwd: Teachin... Darren Cook
- Re: [Computer-go] Fwd: Teachin... Álvaro Begué
- [Computer-go] Teaching Deep Convolutional Neural Network... Hugh Perkins