Jump to content

Efficiently updatable neural network

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by 2a02:2454:8d62:5000:f50e:b7c5:1980:e003 (talk) at 14:59, 24 July 2021 (Removed duplicated internal links [Stockfish, GPU]. Clarified that the last section is specific to shogi.). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

An efficiently updatable neural network (NNUE, sometimes stylised as ƎUИИ) is a neural network-based evaluation function that runs efficiently on central processing units without a requirement for a graphics processing unit (GPU). NNUE was invented by Yu Nasu and introduced to computer shogi in 2018.[1][2] On 6 August 2020, NNUE was for the first time ported to a chess engine, Stockfish 12.[3][4] As of 2021, all of the top rated classical chess engines have a NNUE implementation to remain competetive.

NNUE is used primarily for the leaf nodes of the Alpha–beta tree.[5] While being slower than traditional evaluation functions, NNUE does not suffer from the 'blindness beyond the current move' problem. Stockfish uses NNUE for candidate moves, move selection and move generation.[6]

Compared to neural network evaluation based on dedicated GPUs, NNUE avoids idle times during the substantial data transfer operations between GPU and CPU required before and after each evaluation.[citation needed]

The neural network used by shogi consists of four weight layers: W1 (16-bit integers) and W2, W3 and W4 (8-bit). Incremental computation and single instruction multiple data (SIMD) techniques are used with appropriate intrinsic instructions, specifically in the 2018 computer shogi implementation VPADDW, VPSUBW, VPMADDUBSW, VPACKSSDW, VPACKSSWB and VPMAXSB.[1]

See also

References

  1. ^ a b Yu Nasu (April 28, 2018). "Efficiently Updatable Neural-Network-based Evaluation Function for computer Shogi" (PDF) (in Japanese).
  2. ^ Yu Nasu (April 28, 2018). "Efficiently Updatable Neural-Network-based Evaluation Function for computer Shogi (Unofficial English Translation)" (PDF).
  3. ^ "Introducing NNUE Evaluation". 6 August 2020.
  4. ^ Joost VandeVondele (July 25, 2020). "official-stockfish / Stockfish, NNUE merge".
  5. ^ "Stockfish 12". Stockfish Blog. Retrieved 19 October 2020.
  6. ^ "Stockfish - Chessprogramming wiki". www.chessprogramming.org. Retrieved 2020-08-18.