25,161
edits
Changes
no edit summary
Anyway, a fix from rotate to flip has to be done from producer and consumer sides, and is likely to void some training sessions.
=[[Yu Nasu]] suggestionsSuggestions=
In reply to [[Unai Corzo]], [[Yu Nasu]] suggested 3 techniques that applied successfully to Shogi and can be brought back to Stockfish NNUE and may improve it another 100 - 200 Elo <ref>[http://yaneuraou.yaneu.com/2020/08/21/3-technologies-in-shogi-ai-that-could-be-used-for-chess-ai/ 3 technologies in shogi AI that could be used for chess AI], [[Yu Nasu]], August 2020</ref> <ref>[https://github.com/official-stockfish/Stockfish/issues/2915#issuecomment-678112885, GitHub - NNUE ideas and discussion (post-merge). #2915], August 2020</ref>:
* Optimizing all parameters together by [https://en.wikipedia.org/wiki/Stochastic_optimization stochastic optimization]
* Automatic generation of [[Opening Book|opening book]] on the fly
=Quick NNUE solution for other chess enginesElsewhere=Being tempted by the success of Stockfish NNUE and attracted by how easy the method and small the code is, many engines' engine developers have started testing and applying [[NNUE]]. For quick trying trials and evaluating before going into serious development, some of them borrow borrowed and/or rewrite a bit the rewrote NNUE code and use direct networks of from Stockfish NNUE. Most of them reported positive results, such as [[David Carteau]] with [[Orion]] <ref>[http://talkchess.com/forum3/viewtopic.php?f=2&t=74828 Orion 0.7 : NNUE experiment] by [[David Carteau]], [[CCC]], 19 Aug 2020</ref>, various [[Stockfish#Derivatives|Stockfish derivatives]] by [[Michael Byrne]] <ref>[http://talkchess.com/forum3/viewtopic.php?f=2&t=74825 ... the last shall be first ...] by [[Michael Byrne|MikeB]], [[CCC]], 19 Aug 2020</ref>, and [[Volodymyr Shcherbyna]] with [[Igel]] <ref>[http://talkchess.com/forum3/viewtopic.php?f=2&t=67890&start=10#p856742 Introducing Igel chess engine] by [[Volodymyr Shcherbyna]], [[CCC]], 20 Aug 2020</ref>, to name a few.
=See also=
