25,161
edits
Changes
no edit summary
and the computer chess community bursts out enthusiastically due to its rapidly raising [[Playing Strength|playing strength]] with different networks trained using a mixture of [[Supervised Learning|supervised]] and [[Reinforcement Learning|reinforcement learning]] methods -
despite the approximately halved search speed, seemingly becoming stronger than its original <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74484 Can the sardine! NNUE clobbers SF] by [[Henk Drost]], [[CCC]], July 16, 2020</ref>. In July 2020, the playing code of NNUE is put into the official Stockfish repository as a branch for further development and examination. However, the training code still remains in Nodchip's repository <ref>[https://github.com/official-stockfish/Stockfish/issues/2823 NNUE merge · Issue #2823 · official-stockfish/Stockfish · GitHub] by [[Joost VandeVondele]], July 25, 2020</ref> <ref>[https://github.com/nodchip/Stockfish GitHub - nodchip/Stockfish: UCI chess engine] by [[Nodchip]]</ref>.
=NNUE Structure=
The [[Neural Networks|neural network]] consists of four layers. The input layer is heavily overparametrized, feeding in the [[Board Representation|board representation]] for various king configurations.
The efficiency of [[NNUE]] is due to [[Incremental Updates|incremental update]] the input layer outputs in [[Make Move|make]] and [[Unmake Move|unmake move]],
where only a tiny fraction of its neurons need to be considered. The remaining three layers with 256x2x32-32x32-32x1 neurons are computational less expensive, best calculated using appropriate [[SIMD and SWAR Techniques|SIMD instructions]] like [[AVX2]] on [[x86-64]], or if available, [[AVX-512]].
=Strong Points=
