Re: [Computer-go] What hardware to use to train the DNN
As I understand it: for C/C++ VS Code is just an editor not a compiler or debugger. But as VS 2015 can already work with LLDB and gdb it is only a question of time and free licensing of more .NET parts, I assume. - Michael. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] DCNN can solve semeai?
Hi, I would expect this to happen if the system is trained by normal games, only. But I think the system should see actual live-and-death (LD) sequences (from some collection) to be able to learn about them and not soak this knowledge up from a whole game where most of the moves are "noise" compared to what you ask it to do later. So the training data could be half and half normal games and LD sequences. - Michael. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Board evaluation using a convolutional neural network
Hi, My experience is the same: My CNN was a very poor judge of life and death. Part of the problem is that I couldn't get Pachi to behave exactly the way I wanted (play to maximize score; play to the bitter end, assuming everything left after two passes is considered alive). But perhaps there is some deeper problem, or we are just missing an important twist to make the technique work. I think the problem with live and death is that if it comes to a group that will die the pro will resign; if he can save the group the bot may not even got it that there might have been a live and death issue. So, why can't you train the DNN on pure live and death problems, just like human players do it - from time to time. There are many collections (some even with solutions). - Michael. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] Board evaluation using a convolutional neural network
Well my point is more in the direction to get a good live-and-death solver, maybe completely independent of the game as a whole. Just train a DNN on some life-and-death collections with solutions, where all of the usual tricks are applied. I think this has the potential to get similar if not better results than an engine that is based on theories. Or has this been already tried? - Michael. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
[Computer-go] DCNNigo*
Hi, Lately I saw 4 bots DCNNigo* playing on KGS with different strength. What is the difference between them? - Michael. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
Re: [Computer-go] CGOS future
And using a clearly defined http web server protocol, probably built around json, and then the clients will take care of themselves: all modern languages, except C/C++, come with a good web client library, and a good json library. Just hand out a helper C library, perhaps with a C++ wrapper API. I agree! If you want to write in C/C++ you can use Qt for that: web client and JSON-support. Qt is open source (for open source projects). - Michael. ___ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go