NNUE (Efficiently Updatable Neural Networks) is Stockfish’s modern evaluation method, where a lightweight neural network learns positional patterns—king safety, piece-square relationships, pawn structure, activity, etc.—and outputs a numerical score for any position. Unlike large GPU-based networks, NNUE runs extremely fast on CPUs because it updates only the parts of the network affected by the last move, rather than recomputing everything from scratch. This gives Stockfish both the tactical strength of traditional handcrafted evaluation and the pattern-recognition ability of neural nets. It is the reason Stockfish’s “sense” of piece coordination and king danger became dramatically stronger after 2020.

Referenced in:

• stockfish