Efficiently updatable neural network

An efficiently updatable neural network (NNUE, a Japanese wordplay on 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 table.[1] NNUE is used primarily for the leaf nodes of the alpha–beta tree.[2] While being slower than handcrafted evaluation functions, NNUE does not suffer from the 'blindness beyond the current move' problem.[3]

NNUE was invented by Yu Nasu and introduced to computer shogi in 2018.[4][5] On 6 August 2020, NNUE was for the first time ported to a chess engine, Stockfish 12.[6][7] Since 2021, many 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 (CPU) without a requirement for a graphics processing unit (GPU).[8][9] In contrast, deep neural network-based chess engines such as Leela Chess Zero require a GPU.[10][11]

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). It has 4 fully-connected layers, ReLU activation functions, and outputs a single number, being the score of the board.

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.[4]

See also

• elmo (shogi engine)
• Stockfish chess engine - The chapter about NNUE features a visualization of NNUE.
• List of chess software

References

1. Gary Linscott (April 30, 2021). "NNUE". GitHub. Retrieved December 12, 2020.
2. "Stockfish 12". Stockfish Blog. Retrieved 19 October 2020.
3. "Stockfish - Chessprogramming wiki". www.chessprogramming.org. Retrieved 2020-08-18.
4. Yu Nasu (April 28, 2018). "Efficiently Updatable Neural-Network-based Evaluation Function for computer Shogi" (PDF) (in Japanese).
5. Yu Nasu (April 28, 2018). "Efficiently Updatable Neural-Network-based Evaluation Function for computer Shogi (Unofficial English Translation)" (PDF). GitHub.
6. "Introducing NNUE Evaluation". 6 August 2020.
7. Joost VandeVondele (July 25, 2020). "official-stockfish / Stockfish, NNUE merge". GitHub.
8. "Stockfish FAQ: Can Stockfish use my GPU?". Stockfish. Retrieved 19 January 2025.
9. "nnue-pytorch/docs/nnue.md".
10. Dominik Klein, Neural Networks for Chess, p. 49
11. Monroe, Daniel; Chalmers, Philip A. (2024-10-28), Mastering Chess with a Transformer Model, doi:10.48550/arXiv.2409.12272, retrieved 2024-11-29

External links

• NNUE on the Chess Programming Wiki.
• NNUE evaluation functions for computer shogi on github.com