Published in the journal ‘Proceedings of the National Academy of Sciences (PNAS) on November 14, a study reveals that the neural network engine AlphaZero learns chess by playing against itself and reliably wins games against top human chess players. According to a team of researchers, the neural network interpretability is a research area that encompasses a wide range of approaches and challenges. Our interest in relating network activations to human concepts means we focus primarily on so-called concept-based explanations.
About the Author
