Search found 75 matches

by fabianVDW
Thu Nov 28, 2019 11:06 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: The Mad Woman And The Octopus
Replies: 12
Views: 804

Re: The Mad Woman And The Octopus

Thanks for the tournament Graham! Fab did pretty well in my opinion!
by fabianVDW
Sun Nov 24, 2019 2:47 pm
Forum: Computer Chess Club: General Topics
Topic: New engine releases 2019
Replies: 438
Views: 106720

Re: New engine releases 2019

I have a new version of Fabchess at: https://github.com/fabianvdW/FabChess/releases/tag/v.1.13 This version increases the playing strength of Fabchess, preparing its appearance in TCEC. Changes done: - Decrease LMR - Restructure the Transposition Table. New replacement schema and introduce buckets. ...
by fabianVDW
Sun Oct 27, 2019 9:58 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: deep history pruning
Replies: 8
Views: 1289

Re: deep history pruning

If you try the history scores indexed by ply, let me know how this worked out for you Vivien, this has been on my "Try THIS" list for along time now and I haven't come around to do it... But hearing what bob has said maybe it would be more sensible to have history scores indexed by subtree, but this...
by fabianVDW
Mon Oct 21, 2019 9:16 pm
Forum: Computer Chess Club: General Topics
Topic: Poll: How Many "Weights" Needed To Play "Known" Chess Very Well?
Replies: 34
Views: 1849

Re: Poll: How Many "Weights" Needed To Play "Known" Chess Very Well?

Well, the weights ('eval parameters') in a conventional evaluation are usually tuned, e.g. by Texel tuning. In fact the back-propagation used in a NN is nothing but Texel tuning of the NN. So my answer still stands. I like that you bring this up, because most are not aware of the similarity of the ...
by fabianVDW
Mon Oct 21, 2019 11:35 am
Forum: Computer Chess Club: General Topics
Topic: Poll: How Many "Weights" Needed To Play "Known" Chess Very Well?
Replies: 34
Views: 1849

Re: Poll: How Many "Weights" Needed To Play "Known" Chess Very Well?

Stockish does use a raw board representation as input for the evaluation, doesn't it? I think what Fabian was saying was that, in order to get a NN to evaluate a chess position reasonably well with just a few hundred weights you're proposing that, in your words, "The weights are piece (or piece-squ...
by fabianVDW
Mon Oct 21, 2019 9:24 am
Forum: Computer Chess Club: General Topics
Topic: Poll: How Many "Weights" Needed To Play "Known" Chess Very Well?
Replies: 34
Views: 1849

Re: Poll: How Many "Weights" Needed To Play "Known" Chess Very Well?

It depends on how you define "very well". If you are happy with Stockfish, the answer is "a couple of hundred". Conventional evaluations can be implemented as Neural networks with a one or two layers. The weights are piece (or piece-square) values, passer bonuses etc. If you are happy with micro-Ma...
by fabianVDW
Sun Oct 20, 2019 12:04 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: 76th Amateur Series Division 6
Replies: 12
Views: 1893

Re: 76th Amateur Series Division 6

Thanks Graham, very nice tournament!

Congrats to Luigi and ECE for having made quite the comeback in the later half of the tournament ;)
by fabianVDW
Sun Oct 13, 2019 12:53 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: CEGT - rating lists October 13th 2019
Replies: 1
Views: 1081

Re: CEGT - rating lists October 13th 2019

Thanks a lot for testing FabChess :)
by fabianVDW
Fri Oct 11, 2019 4:24 pm
Forum: Computer Chess Club: General Topics
Topic: New engine releases 2019
Replies: 438
Views: 106720

Re: New engine releases 2019

I have a new version of FabChess at https://github.com/fabianvdW/FabChess/releases/tag/v.1.12.8 This version finally introduces SMP for FabChess - and with it comes more UCI functionality. Changelog: - FabChess now supports multithreading for an arbitrary amount of threads. The UCI settings now addi...
by fabianVDW
Mon Oct 07, 2019 4:30 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: A book on machine learning
Replies: 7
Views: 1887

Re: A book on machine learning

I took a quick look at the content, and it seems there is extremely little machine learning in this book, except for a decision tree in Chapter 2. Mostly genetic algorithms and population-based methods. No neural network. But what they describe may be fun programming experiments. AFAIK genetic algo...