Re: [Computer-go] Forecasting Lee Sedol vs. AlphaGo

Hello, the "Good judgement"-site is somewhat strange. Why do they give April 01 as closing date, when the match will take place already in mid March? *** Some side information: In Germany's computer go forum we also have a forecast. So far 52 registered members gave their

Re: [Computer-go] Neural Net move prediction

Sounds like some kind of boosting, I suppose? On Thu, Feb 4, 2016 at 7:52 PM Marc Landgraf wrote: > Hi, > > lately a friend and me wondered about the following idea. > > Let's assume you have a reasonably strong move prediction DCNN. What > happens if you now train a

Re: [Computer-go] Mathematics in the world

Robert, Just as an aside, I really respect your attention to detail and your insistence that proof technique follow generalizing statements about aspects of go. I think that the counting problems recently were pretty interesting (number of positions versus number of games). The engineering

Re: [Computer-go] AlphaGo and the Standard Mistake in Research and Journalism

Not to beat a dead horse, but big numbers aren't inherently interesting to describe. There are integers bigger than any integer anyone has written down in any form. This particular integer is large, but "consumable". I guess I get tired of the "number of atoms in the observable universe"

Re: [Computer-go] Neural Net move prediction

The method is not likely to work, since the goal of NN training s to reduce the residual error to a random function of the NN inputs. If the NN succeeds at this, then there will be no signal to train against. If the NN fails, then it could be because the NN is not large enough, or because there

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

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 > One possibility is that 0=loss, 1=win, and the number they are quoting is > sqrt(average((prediction-outcome)^2)). this makes perfectly sense for figure 2. even playouts seem reasonable. But figure 2 is not consistent with the numbers in section

Re: [Computer-go] What hardware to use to train the DNN

David, You're a trooper for doing this in windows. :) The OS overhead is generally lighter if you use unix; even the most modern windows versions have a few layers of slowdown. Unix (for better or worse) will give you closer, easier access to the hardware, and closer, easier access to halting

Re: [Computer-go] What hardware to use to train the DNN

I’ll do training on Linux for performance, and because it is so much easier to build than on Windows. I need something I can ship to my windows customers, that is light weight enough to play well without a GPU. All of my testing and evaluation machines and tools are on Windows, so I can’t

Re: [Computer-go] What hardware to use to train the DNN

Welll, David is making a product. Making a product is 'trooper' solution unless you are making very specific product to a very narrow target group, willing to pay thousands for single license Petri 2016-02-04 23:50 GMT+02:00 uurtamo . : > David, > > You're a trooper for doing

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

Detlef Schmicker: <56b385ce.4080...@physik.de>: >-BEGIN PGP SIGNED MESSAGE- >Hash: SHA1 > >Hi, > >I try to reproduce numbers from section 3: training the value network > >On the test set of kgs games the MSE is 0.37. Is it correct, that the >results are represented as +1 and -1? Looks

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

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 >> Since all positions of all games in the dataset are used, winrate >> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the >> number 70% could be wrong. MSE is 0.37 just means the average >> error is about 0.6, I think. 0.6 in the

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

I am not sure how exactly they define MSE. If you look at the plot in figure 2b, the MSE at the very beginning of the game (where you can't possibly know anything about the result) is 0.50. That suggests it's something else than your [very sensible] interpretation. Álvaro. On Thu, Feb 4, 2016

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

The positions they used are not from high-quality games. They actually include one last move that is completely random. Álvaro. On Thursday, February 4, 2016, Detlef Schmicker wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA1 > > Hi, > > I try to reproduce numbers from

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

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Hi, I try to reproduce numbers from section 3: training the value network On the test set of kgs games the MSE is 0.37. Is it correct, that the results are represented as +1 and -1? This means, that in a typical board position you get a value of

Re: [Computer-go] Neural Net move prediction

Sounds similar to adversarial networks On Thu, Feb 4, 2016, 04:50 Huazuo Gao wrote: > Sounds like some kind of boosting, I suppose? > > On Thu, Feb 4, 2016 at 7:52 PM Marc Landgraf wrote: > >> Hi, >> >> lately a friend and me wondered about the

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

-BEGIN PGP SIGNED MESSAGE- Hash: SHA1 Thanks for the response, I do not refer to the finaly used data set: in the referred chapter they state, they have used their kgs dataset in a first try (which is in another part of the paper referred to being a 6d+ data set). Am 04.02.2016 um 18:11

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

I re-read the relevant section and I agree with you. Sorry for adding noise to the conversation. Álvaro. On Thu, Feb 4, 2016 at 12:21 PM, Detlef Schmicker wrote: > -BEGIN PGP SIGNED MESSAGE- > Hash: SHA1 > > Thanks for the response, I do not refer to the finaly

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

That sounds like it'd be the MSE as classification error of the eventual result. I'm currently not able to look at the paper, but couldn't you use a softmax output layer with two nodes and take the probability distribution as winrate? On Thu, Feb 4, 2016 at 8:34 PM, Álvaro Begué

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

I think the error is defined as the difference between the output of the value network and the average output of the simulations done by the policy network (RL) at each position. Hideki Michael Markefka:

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

I just want to see how to get 0.5 for the initial position on the board with some definition. One possibility is that 0=loss, 1=win, and the number they are quoting is sqrt(average((prediction-outcome)^2)). On Thu, Feb 4, 2016 at 3:40 PM, Hideki Kato wrote: > I think