Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

2016-01-29 Thread Detlef Schmicker
-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hi Ingo, I think you are not alone: When I started computer go 4 years ago I ask a good friend of mine, who did his PhD in Neural Networks back in the 90s, if I have any chance to use them instead of pattern matching and he said, they will probably no

Re: [Computer-go] Mastering the Game of Go with Deep Neural Networks and Tree Search

2016-01-29 Thread Erik van der Werf
This fluctuating sentiment on artificial neural networks is a bit weird; popularity comes and goes in waves, and many academics appear to be just following the hype. Most of the stuff I learned on ANN's in the 90s and early zeros just works, and now we can see that if one throws huge computational

Re: [Computer-go] Replicating AlphaGo results

2016-01-29 Thread Brian Cloutier
> Even if you have a lot of hardware, it's *hard* to make it add value, as anyone who tried to run MCTS on a cluster could testify - it's not just a matter of throwing it at the problem, and the challenges aren't just engineering-related either. For those of us who don't know, could you talk a lit