Neural networks in chess programming
Alpha Zero has revolutionised chess programming. The programme taught itself chess by playing against itself and storing its training knowledge in a neural network. All programmes have followed suit with this technique. Roger Lorenz uses a simple example to show how neural networks work and how they can be trained.
Guido Van Rossum Stanford University Stockfish Efficiently Updated Neural Network Evaluation Chess Software World Champion Facebook Ai Research World Championship
Source: chessbase.com