Search found 206 matches

by Tony P.
Tue Sep 29, 2020 6:42 pm
Forum: Computer Chess Club: General Topics
Topic: A Crossroad in Computer Chess; Or Desperate Flailing for Relevance
Replies: 152
Views: 17075

Re: A Crossroad in Computer Chess; Or Desperate Flailing for Relevance

I'd say 80% of NN papers don't have any advanced math in them. It's a bit of a problem for the field - there is a lot of experimentation but less theory about why this works and this doesn't. So it's still possible to make a lot of progress without being a mathematician. A bigger problem is the lac...
by Tony P.
Tue Sep 29, 2020 6:32 pm
Forum: Computer Chess Club: General Topics
Topic: Is Allie a 'Leela net player'?
Replies: 57
Views: 7368

Re: Is Allie a 'Leela net player'?

I consider the S14 NN rules still relevant. If they're applied to CPU NNs too, then there can only be one NNUE player at TCEC - SF itself - unless someone writes a training algorithm that gains a ton of rating points over SF's, which is hard because the nets are small. I won't be surprised if Leela ...
by Tony P.
Tue Sep 29, 2020 5:57 pm
Forum: Computer Chess Club: General Topics
Topic: A Crossroad in Computer Chess; Or Desperate Flailing for Relevance
Replies: 152
Views: 17075

Re: A Crossroad in Computer Chess; Or Desperate Flailing for Relevance

I won't use Stockfish's methods. I'm adding my own NN ideas to Ethereal, but it bores me. I'm praying that one can beat NNUE King-Piece networks with some brilliant architecture. But my hopes fall each day. You can beat them. You just need patience, may need to try several arch. before you find a b...
by Tony P.
Mon Sep 28, 2020 6:38 pm
Forum: Computer Chess Club: Tournaments and Matches
Topic: SPCC: Testrun of Ethereal 12.62 finished
Replies: 13
Views: 2442

Re: SPCC: Testrun of Ethereal 12.62 finished

Nope. NNUE is a one way ticket to kill the originality of the engine. When people talk about NNUE, I'm not always sure if they mean sparse nets in general or the exact architecture used in SF (it looks like you meant the latter, which is how I use the NNUE term too). The reuse of the exact network ...
by Tony P.
Mon Sep 28, 2020 5:54 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Re-activation Programmer Code of Honor
Replies: 57
Views: 9748

Re: Re-activation Programmer Code of Honor

It's almost impossible to build something 100% original; maybe Leela may qualify The legacy lczero backend was an adaptation of GCP's Leela Zero repository to chess, using Stockfish's position representation and move generation. (No heuristics or prior knowledge are carried over from Stockfish.) as...
by Tony P.
Sun Sep 27, 2020 9:24 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: Re-activation Programmer Code of Honor
Replies: 57
Views: 9748

Re: Re-activation Programmer Code of Honor

Thank you for the peacemaking effort, Ed. I hope it makes the attitudes to respectful derivatives less negative. Sorry for overthinking and commenting as a nonprogrammer, but fwiw, I don't think clause 3 should cover those ideas that haven't been applied to chess nor chesslike board games yet. Those...
by Tony P.
Sat Sep 26, 2020 8:44 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: "It must be a clone of some sort..."
Replies: 50
Views: 11079

Re: "It must be a clone of some sort..."

If you opensource an early, much weaker, version of an engine that you're releasing without the current source, then it's hardly a mortification because it's known that your coding skills have improved since the early days because your engine now plays strong. The weaker version serves as a proof of...
by Tony P.
Sat Sep 26, 2020 8:23 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: In today's environment ...
Replies: 8
Views: 1832

Re: In today's environment ...

It is difficult to know what to do with the information that comes from a fast lazy evaluation. It should not be stored in the hash table. The table could have separate fields for different stage evals, but that would increase the entry size. I'm not sure how big of an issue this memory inefficienc...
by Tony P.
Sat Sep 26, 2020 7:32 pm
Forum: Computer Chess Club: General Topics
Topic: 'Age of Caissa', a chess manga by Youtuber agadmator
Replies: 0
Views: 1653

'Age of Caissa', a chess manga by Youtuber agadmator

As per the video description: Finally – it’s here – Chess manga – Age of Caissa. Over a year in prep, this was a huge creative effort of a small but focused team of artists, writers, scientists, philosophers (yes, really) and what we end up with is not just a manga (available free online or bought a...
by Tony P.
Fri Sep 25, 2020 8:11 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: In today's environment ...
Replies: 8
Views: 1832

Re: In today's environment ...

Do you mean 'lazy evaluation' ? I guess it's worth a try in an engine with a heavy eval, e.g. a neural net can be restructured in the BranchyNet fashion and retrained. The lazy approach seems inefficient in engines with lightweight evals where the time savings aren't big enough to compensate for the...