Google DeepMind's 'superhuman' AlphaZero computer taught ITSELF to

GOOGLE has created an artificial intelligence so clever it can teach itself to become a "master" of chess. Normally AI learns based on existing data – like watching chess masters player – but AlphaZero earned "superhuman mastery" just by playing against itself.

Google says it built a 'superhuman' game-playing AI. Is it truly intelligent?, NOVA

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

DeepMind computer teaches itself to become world's best Go player

How DeepMind's AlphaGo Became the World's Top Go Player, by Andre Ye

AlphaGo Zero Shows Machines Can Become Superhuman Without Any Help

Acquisition of chess knowledge in AlphaZero

AlphaZero AI beats champion chess program after teaching itself in four hours, DeepMind

AlphaGo Zero: Google DeepMind supercomputer learns 3,000 years of human knowledge in 40 days

Google's AlphaZero Masters Chess, Go and Shogi in 24 Hours

AlphaGo Zero: Google DeepMind supercomputer learns 3,000 years of human knowledge in 40 days

AI, Free Full-Text