Search found 493 matches

by brianr
Sun Jul 18, 2021 7:09 pm
Forum: Computer Chess Club: General Topics
Topic: Fat Fritz question
Replies: 11
Views: 1608

Re: Fat Fritz question

I would hardly characterize it as trivial, even for the vastly simpler SF-NNUE type nets (as I mentioned).
Naturally, for both types of nets after you have done a few it does become pretty straightforward.
by brianr
Sun Jul 18, 2021 6:55 pm
Forum: Computer Chess Club: General Topics
Topic: Fat Fritz question
Replies: 11
Views: 1608

Re: Fat Fritz question

Of course not, and I'm a bit surprised you don't know. Matt Lai is the Giraffe author and went on to DeepMind and AZ. https://www.chessprogramming.org/Giraffe I got to where I could understand the code enough to get Giraffe training to start. By the time I figured it out Leela Chess was starting up ...
by brianr
Sun Jul 18, 2021 5:10 pm
Forum: Computer Chess Club: General Topics
Topic: Fat Fritz question
Replies: 11
Views: 1608

Re: Fat Fritz question

There are two Fat Fritz engines. The first used the Leela Chess project quite heavily. The second FF2 used the Stockfish project with the relatively recent NNUE additions. The primary person developing both is Albert Silver. See: https://www.chessprogramming.org/Albert_Silver note the links to Deus ...
by brianr
Tue Jul 13, 2021 4:38 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Two fold or three fold repetition?
Replies: 5
Views: 1784

Re: Two fold or three fold repetition?

FWIW I follow Crafty's approach and count 3 reps at the root and only 2 during the search as draws.
by brianr
Tue Apr 27, 2021 11:59 pm
Forum: Computer Chess Club: General Topics
Topic: Lc0 question
Replies: 17
Views: 5212

Re: Lc0 question

Trying to understand why the Lc0 search depth in the endgame drops from 12.74 -> 8.75 -> 7.64 while it should be the other way around. There is no depth with Lc0 that is comparable to depth in A/B engines. The reported Lc0 depth is actually just an estimate and is based on total playouts, and playo...
by brianr
Sat Mar 20, 2021 2:17 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: CCRL 40/15, 40/2 and FRC lists updated (6th March 2021)
Replies: 17
Views: 3594

Re: CCRL 40/15, 40/2 and FRC lists updated (6th March 2021)

There is little need to limit CPU cores for GPU engines such as Lc0 and the like. The general rule of thumb is threads should be the number of GPUs plus 1 only. More threads may show faster nps, but playing strength does not improve and could get worse. CPU RAM memory (nncache setting) is a manageab...
by brianr
Tue Feb 23, 2021 4:30 pm
Forum: Computer Chess Club: General Topics
Topic: Are neural nets (the weights file) copyrightable?
Replies: 473
Views: 43256

Re: Are neural nets (the weights file) copyrightable?

But, as you say, the goal is to improve strength. Innovations in Formula 1 cars aren't copyrightable if they aim to increase the car's performance rather than its aesthetics. You say tomato, I say ... For many, strong chess play is beautiful. Separately, does aesthetics have anything to do with "ar...
by brianr
Tue Feb 23, 2021 11:47 am
Forum: Computer Chess Club: General Topics
Topic: Are neural nets (the weights file) copyrightable?
Replies: 473
Views: 43256

Re: Are neural nets (the weights file) copyrightable?

Machine-generation of a NN is hard to argue that a major effort of human creativity is needed to accomplish. The person arguing copyright must show that it required some personal/human creative unique effort for copyright to be possible, At least in US law. Creativity is certainly required to train...
by brianr
Sun Feb 21, 2021 8:38 pm
Forum: Computer Chess Club: General Topics
Topic: Are neural nets (the weights file) copyrightable?
Replies: 473
Views: 43256

Re: Are neural nets (the weights file) copyrightable?

But those are the works of human authors and creative works. They're also not derivative works of GPL'd software. But suit yourself to a double standard. Training a basic net from instructions is fairly straightforward, although there are many quite exacting steps. Carefully testing and measuring i...
by brianr
Mon Feb 15, 2021 10:20 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Improving move ordering question
Replies: 3
Views: 1172

Re: Improving move ordering question

Every engine has its own ecosystem of what works best. For Tinker (FWIW) my order is different: HashMove PVMove InCheck (evasions) GoodCaptures Killers (Better to do killers after captures and only store non-captures as killers) NonCaptures PoorCaptures Each move is only tried one time, so for examp...