Understanding AlphaZero Neural Network's SuperHuman Chess Ability

As a common and (sometimes) proven belief, deep learning systems seem to learn uninterpretable representations and are far from human understanding. Recently, some studies have highlighted the fact that this may not always be applicable, and some networks may be able to learn human-readable representations. Unfortunately, this ability could merely come from the fact that these networks are exposed to human-generated data. So, to demonstrate their ability to learn like humans (and not that they are simply memorizing human-created labels), it is necessary to test them without any label.  Following this idea, the DeepMind and Google Brain teams, together with

Acquisition of chess knowledge in AlphaZero

The human side of AI for chess - Microsoft Research

[Sadler, Matthew, Regan, Natasha, Kasparov, Garry] on . *FREE* shipping on qualifying offers. Game Changer: AlphaZero's Groundbreaking

Game Changer: AlphaZero's Groundbreaking Chess Strategies and the Promise of AI

Mastering the game of Go with deep neural networks and tree search

A general reinforcement learning algorithm that masters chess, shogi and Go through self-play: A Quick Summary, by Ali Abidi

A Very Unlikely Chess Game

DeepMind, Google Brain & World Chess Champion Explore How AlphaZero Learns Chess Knowledge

Reimagining Chess with AlphaZero, February 2022

What makes Alpha Zero so much ahead of the most powerful chess engines out there? - Quora