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…

Stockfish - Chess Engines

How monumental are Deepmind's achievements in Neural Networks?, by Stephen Tse

What Is a Chess Engine? Types and Winning Practices Unveiled

Has Stockfish ever lost?

GitHub - joergoster/Stockfish-old: UCI chess engine

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

Chess.com announces new super-strong chess engine to challenge Stockfish - Dot Esports

Introducing NNUE Evaluation - Stockfish - Open Source Chess Engine

Stockfish 15 vs Stockfish 11, the Last Version without NNUE!

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

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

The chess games of Stockfish (Computer)