The neural network of the Stockfish chess engine

Last time, we briefly mentioned the high-level differences between Stockfish and Leela Chess. To recap, Stockfish evaluates about 100 million positions per second using rudimentary heuristics, whereas Leela Chess evaluates 40 000 positions per second using a deep neural network trained from millions of games of self-play. They also use different tree search approaches: Stockfish…

The Basics of Neural Networks for Chess nerds (and anyone interested in AI), by Ryan Leong, Nov, 2023

13 How chess engines work

Dissecting Stockfish Part 2: In-Depth Look at a chess engine, by Antoine Champion

AlphaZero Crushes Stockfish In New 1,000-Game Match

High-level explanation

Bradley Lovell - Polecat

Frontiers Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data

How to set up the Stockfish chess engine to improve your skills - Neowin

Dissecting Stockfish Part 2: In-Depth Look at a chess engine, by Antoine Champion

Kling combination: a self-stalemate theme that perplexes Stockfish - Chess .com

Neural Networks For Chess: The magic of deep and reinforcementlearning revealed: Klein, Dominik: 9798485890537: : Books

AlphaZero Crushes Stockfish In New 1,000-Game Match

GitHub - asdfjkl/neural_network_chess: Free Book about Deep-Learning approaches for Chess (like AlphaZero, Leela Chess Zero and Stockfish NNUE)

Stockfish Wins Computer Chess Championship Rapid; Lc0 Finishes 3rd - Chess .com