25,161
edits
Changes
no edit summary
=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 outputs of 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<ref>[http://www.talkchess.com/forum3/viewtopic.php?f=7&t=74531&start=1 Re: NNUE accessible explanation] by [[Jonathan Rosenthal]], [[CCC]], July 23, 2020</ref>. 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=
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74520 Sergio Vieri second net is out] by Sylwy, [[CCC]], July 21, 2020
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=74531 NNUE accessible explanation] by [[Martin Fierz]], [[CCC]], July 21, 2020
: [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=74531&start=1 Re: NNUE accessible explanation] by [[Jonathan Rosenthal]], [[CCC]], July 23, 2020
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74565 Stockfish NNUE] by Lion, [[CCC]], July 25, 2020
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74585 SF-NNUE going forward...] by Zenmastur, [[CCC]], July 27, 2020
