Re: [Computer-go] "English Explanations" based on Neural Networks

2016-03-31 Thread David Doshay
It all comes down to having a reasonable way to search the MCTS’s tree. An elegant tool would be wonderful, but even something basic would allow a determined person to find interesting things. When I was debugging SlugGo, which had a tree as wide as 24 and as deep as 10, with nothing other than

Re: [Computer-go] "English Explanations" based on Neural Networks

2016-03-31 Thread uurtamo .
Major changes in the evaluation probability could likely have a horizon of a few moves behind that might be interesting to more closely evaluate. With a small window like that, a deeper/more exhaustive search might work. s. On Mar 31, 2016 10:21 AM, "Petr Baudis" wrote: > On Thu,

Re: [Computer-go] "English Explanations" based on Neural Networks

2016-03-31 Thread Jim O'Flaherty
Petr, You know, just exploring this conversation is motivating to me, even if I am still seeing it as huge risk with small payoff. I like your line of thinking in that from a top down approach, we start simple and just push it as far as it can go, acknowledging we won't likely get anywhere near

Re: [Computer-go] "English Explanations" based on Neural Networks

2016-03-31 Thread Petr Baudis
On Thu, Mar 31, 2016 at 08:51:30AM -0500, Jim O'Flaherty wrote: > What I was addressing was more around what Robert Jasiek is describing in > his joseki books and other materials he's produced. And it is exactly why I > think the "explanation of the suggested moves" requires a much deeper > baking

Re: [Computer-go] "English Explanations" based on Neural Networks

2016-03-31 Thread djhbrown .
Petr suggests "caption Go positions based on game commentary" Without doubt, there has to be a lot of mileage in looking for a way for a machine to learn from expert commentaries. i see a difference between labelling a cat in a photo and labelling a stone configuration in a picture of a board,

[Computer-go] "English Explanations" based on Neural Networks

2016-03-31 Thread Petr Baudis
On Wed, Mar 30, 2016 at 09:58:48AM -0500, Jim O'Flaherty wrote: > My own study says that we cannot top down include "English explanations" of > how the ANNs (Artificial Neural Networks, of which DCNN is just one type) > arrive a conclusions. I don't think that's obvious at all. My current avenue