Difference between revisions of "Stockfish NNUE"

From Chessprogramming wiki
Jump to: navigation, search
Line 10: Line 10:
 
In 2019, Nodchip incorporated NNUE into Stockfish 10 - as a proof of concept, and with the intention to give something back to the Stockfish community <ref>[http://yaneuraou.yaneu.com/2020/06/19/stockfish-nnue-the-complete-guide/ Stockfish NNUE – The Complete Guide], June 19, 2020 (Japanese and English)</ref>.
 
In 2019, Nodchip incorporated NNUE into Stockfish 10 - as a proof of concept, and with the intention to give something back to the Stockfish community <ref>[http://yaneuraou.yaneu.com/2020/06/19/stockfish-nnue-the-complete-guide/ Stockfish NNUE – The Complete Guide], June 19, 2020 (Japanese and English)</ref>.
 
After support and announcements by [[Henk Drost]] in May 2020 <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74059 Stockfish NN release (NNUE)] by [[Henk Drost]], [[CCC]], May 31, 2020</ref>  
 
After support and announcements by [[Henk Drost]] in May 2020 <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74059 Stockfish NN release (NNUE)] by [[Henk Drost]], [[CCC]], May 31, 2020</ref>  
−
and subsequent enhancements, Stockfish NNUE was established. In summer 2020 with more people involved in [[Engine Testing|testing]] and training,  
+
and subsequent enhancements, Stockfish NNUE was established and recognized. In summer 2020, with more people involved in [[Engine Testing|testing]] and [[Learning|training]],  
−
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 -
+
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, Stockfish NNUE seemingly became 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>.
−
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=
 
=NNUE Structure=

Revision as of 19:54, 29 July 2020

Home * Engines * Stockfish * NNUE

Toriyama Sekien - Ikuchi [1]

Stockfish NNUE,
a Stockfish branch by Nodchip which uses Efficiently Updatable Neural Networks - stylized as ƎUИИ or reversed as NNUE - to replace its standard evaluation. NNUE, introduced in 2018 by Yu Nasu [2], were previously successfully applied in Shogi evaluation functions embedded in a Stockfish based search [3], such as YaneuraOu [4], and Kristallweizen-kai [5]. In 2019, Nodchip incorporated NNUE into Stockfish 10 - as a proof of concept, and with the intention to give something back to the Stockfish community [6]. After support and announcements by Henk Drost in May 2020 [7] and subsequent enhancements, Stockfish NNUE was established and recognized. In summer 2020, with more people involved in testing and training, the computer chess community bursts out enthusiastically due to its rapidly raising playing strength with different networks trained using a mixture of supervised and reinforcement learning methods. Despite the approximately halved search speed, Stockfish NNUE seemingly became stronger than its original [8]. 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 [9] [10].

NNUE Structure

The neural network consists of four layers. The input layer is heavily overparametrized, feeding in the board representation for various king configurations. The efficiency of NNUE is due to incremental update the outputs of the input layer in make and unmake move, where only a tiny fraction of its neurons need to be considered [11]. The remaining three layers with 256x2x32-32x32-32x1 neurons are computational less expensive, best calculated using appropriate SIMD instructions like AVX2 on x86-64, or if available, AVX-512.

Strong Points

  • Reuses and gets benefits from the very optimized search function of Stockfish as well as almost all Stockfish's code
  • Runs with CPU only, doesn't require expensive video cards, and the need for installing video drivers and specific libraries, thus it becomes much easier to install (compare with other NN engines such as Leela Chess Zero) for users and can run with almost all modern computers
  • Requires much smaller training sets. Some high score networks can be built with the effort of one or a few people. It doesn't require the massive computing from a supercomputer and/or from community

See also

Forum Posts

2020 ...

January ...

July

Re: NNUE accessible explanation by Jonathan Rosenthal, CCC, July 23, 2020

External Links

Chess Engine

Misc

References

  1. ↑ Ikuchi drawn as the Ayakashi from the Konjaku Gazu Zoku Hyakki (今昔画図続百鬼) by Toriyama Sekien, circa 1779, Wikimedia Commons
  2. ↑ Yu Nasu (2018). ƎUИИ Efficiently Updatable Neural-Network based Evaluation Functions for Computer Shogi. Ziosoft Computer Shogi Club, pdf (Japanese with English abstract)
  3. ↑ The Stockfish of shogi by Larry Kaufman, CCC, January 07, 2020
  4. ↑ GitHub - yaneurao/YaneuraOu: YaneuraOu is the World's Strongest Shogi engine(AI player), WCSC29 1st winner, educational and USI compliant engine
  5. ↑ GitHub - Tama4649/Kristallweizen: 第29回世界コンピュータ将棋選手権 準優勝のKristallweizenです。
  6. ↑ Stockfish NNUE – The Complete Guide, June 19, 2020 (Japanese and English)
  7. ↑ Stockfish NN release (NNUE) by Henk Drost, CCC, May 31, 2020
  8. ↑ Can the sardine! NNUE clobbers SF by Henk Drost, CCC, July 16, 2020
  9. ↑ NNUE merge · Issue #2823 · official-stockfish/Stockfish · GitHub by Joost VandeVondele, July 25, 2020
  10. ↑ GitHub - nodchip/Stockfish: UCI chess engine by Nodchip
  11. ↑ Re: NNUE accessible explanation by Jonathan Rosenthal, CCC, July 23, 2020
  12. ↑ An info by Sylwy, CCC, July 25, 2020

Up one Level

Retrieved from "https://www.chessprogramming.org/index.php?title=Stockfish_NNUE&oldid=20392"