Re: [Computer-go] Determining the final board state for finished games

I ended up using gnugo --score aftermath --capture-all-dead to determine the final state of the board. Thanks to Petr for the suggestion! This worked within a 1pt margin of error for probably 95% of the games, which was good enough for my purposes. -Justin

[Computer-go] More data for DNN's?

The Maddison et al, and Clark et. al. papers, http://arxiv.org/pdf/1412.6564v2.pdf http://arxiv.org/abs/1412.3409, both suffer from a lack of very high skilled games, and thus result to using (possibly blitz) games from lower ranked players on KGS. Has there been any effort to gather data from the

[Computer-go] Determining the final board state for finished games

Hello! I'm new to computer Go, it's nice to find this mailing list! I've downloaded the GoGod dataset of completed professional games, and for the games that been fully played out (no resign) I'd like to determine the final state of the board (i.e. which groups are live/dead and what territory

[Computer-go] Simple GUI for visualizing NN probabilities?

Hello, I'm playing around with some of the CNN for move predictions that are out on the web. It'd be nice to have some sort of visual representation of the next move probabilities, does anyone know of some good libraries out there that can do this or at least be relatively easily modified to do

Re: [Computer-go] Using gogui to visualize a CNN for move prediction

Ok I've got a few basic commands like genmove working, however I'm having trouble guessing the response format gogui is expecting for an analyze command I defined. I'm trying to display board influence by defining my own "dboard" command. My analyze config file has the following line:

[Computer-go] Using gogui to visualize a CNN for move prediction

thanks! -Justin Gilmer ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] Board evaluation using a convolutional neural network

Hey everyone, I recently trained a CNN to do board evaluation in Go. You can see the work on github: https://github.com/jmgilmer/GoCNN The network was trained on 15000 professional games which didn't end in resignation, I had the network try to predict the final ownership based on current

Re: [Computer-go] Board evaluation using a convolutional neural network

Quick question: When using this mailing list, how to I explicately reply to a thread, so far I've just been editing the subject and sending it to computer-go@computer-go.org. Regarding use in a MTCS engine, I strongly suspect it would perform poorly in its current form. It is quite poor at life

Re: [Computer-go] Move evalution by expected value, as product of expected winrate and expected points?

I made a similar attempt as Alvaro to predict final ownership. You can find the code here: https://github.com/jmgilmer/GoCNN/. It's trained to predict final ownership for about 15000 professional games which were played until the end (didn't end in resignation). It gets about 80.5% accuracy on a