Jump to content

Efficiently updatable neural network

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by 176.54.252.116 (talk) at 19:58, 13 February 2023 (top: Fixed grammar). 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, a Japanese wordplay on [[Template:Nue]], sometimes stylised as ƎUИИ) is a neural network-based evaluation function whose inputs are piece-square tables, or variants thereof like the king-piece-square {{Cite error: A <ref> tag is missing the closing </ref> (see the help page).}} web | url=https://github.com/glinscott/nnue-pytorch/blob/master/docs/nnue.md | title=NNUE | author=Gary Linscott | date=April 30, 2021 | access-date=December 12, 2020}}</ref> NNUE is used primarily for the leaf nodes of the alpha–beta tree.[1] While being slower than handcrafted evaluation functions, NNUE does not suffer from the 'blindness beyond the current move' problem.[2]

NNUE was invented by Yu Nasu and introduced to computer shogi in 2018.[3][4] On 6 August 2020, NNUE was for the first time ported to a chess engine, Stockfish 12.[5][6] Since 2021, all of the top rated classical chess engines such as Komodo Dragon have an NNUE implementation to remain competitive.

NNUE runs efficiently on central processing units without a requirement for a graphics processing unit (GPU).

The neural network used for the original 2018 computer shogi implementation consists of four weight layers: W1 (16-bit integers) and W2, W3 and W4 (8-bit). W1 encoded the king's position and therefore this layer needed only to be re-evaluated once the king moved. It used incremental computation and single instruction multiple data (SIMD) techniques along with appropriate intrinsic instructions.[3]

See also

References

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