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

Deep neural networks are known to learn opaque, uninterpretable representations that lie beyond the grasp of human understanding. As such, from both scientific and practical viewpoints, it is intriguing to explore what is actually being learned and how in the case of superhuman self-taught neural network agents such as AlphaZero. In the new paper Acquisition

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

Google DeepMind Researchers Uncover the Power of AI Diversity in Tackling Chess Challenges: Introducing AZ_db, the Next Leap in Computational Problem-Solving - MarkTechPost

Living under AI supremacy: Five lessons learned from chess

Google Deep Mind AI Alpha Zero Devours Stockfish

Google's New AI Is a Master of Games, but How Does It Compare to the Human Mind?, Innovation

Google's New AI Is a Master of Games, but How Does It Compare to the Human Mind?, Innovation

Google's DeepMind robot becomes world-beating chess grandmaster in four hours

Acquisition of chess knowledge in AlphaZero

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

Deepmind AlphaZero - Mastering Games Without Human Knowledge