Re: [computer-go] November KGS bot tournament: 19x19 boards, fast

2009-11-03 Thread Nick Wedd
I have now received "unofficial" entries from GNU Go (Aloril) and MoGo (Petr Baudis). I may receive one from Fuego (Aloril again, but with inadequate processor power). I am grateful for these, it is good to see how the strong players perform. All of these will step down if I receive an offic

Re: [computer-go] Neural networks

2009-11-03 Thread Willemien
I disagree with the point that MCTS is a neural network, In my opinion (and i maybe completely off target) One of the essences of neural networks is that the program changes/learns from the games it has played. . MCTS doesn't have that result, the improvement is only "in-game" The program doesn't

Re: [computer-go] Neural networks

2009-11-03 Thread steve uurtamo
these things have definitions, folks. everything isn't everything else. s. On Tue, Nov 3, 2009 at 7:43 AM, Willemien wrote: > I disagree with the point that MCTS is a neural network, > > In my opinion (and i maybe completely off target) One of the essences > of neural networks is that the progr

Re: [computer-go] Neural networks

2009-11-03 Thread Richard Brown
On Tue, Nov 3, 2009 at 6:43 AM, Willemien wrote: > I disagree with the point that MCTS is a neural network, > > In my opinion (and i maybe completely off target) One of the essences > of neural networks is that the program changes/learns from the games > it has played. . I think that you are righ