25,161
edits
Changes
NNUE
,no edit summary
=NN Structure=
The neural network consists of four layers, W1 through W4. The input layer W1 is heavily overparametrized, feeding in the [[Board Representation|board representation]] for various king and pawn configurations.
The efficiency of the net is due to [[Incremental Updates|incremental update]] of W1 in [[Make Move|make]] and [[Unmake Move|unmake move]],
where only a fraction of its neurons need to be recalculated. The remaining three layers with 256x2256x2x32-3232x32-32 channels 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]].
[[FILE:NNUE.jpg|none|border|text-bottom]]
* [https://www.qhapaq.org/shogi/shogiwiki/stockfish-nnue/ Stockfish NNUE Wiki]
* [https://github.com/official-stockfish/Stockfish/issues/2823 NNUE merge · Issue #2823 · official-stockfish/Stockfish · GitHub] by [[Joost VandeVondele]], July 25, 2020 <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74560 An info] by Sylwy, [[CCC]], July 25, 2020</ref>
* [https://www.comp.nus.edu.sg/~sergio-v/nnue/ Index of /~sergio-v/nnue] by [[Sergio Vieri]]
=References=
<references />
'''[[Neural Networks|Up one Level]]'''
