AI and Information Theory

highlighted by JP Bouchaud

Statistical Criticality arises in Most Informative Representations

• Why does deep and cheap learning work so well? Henry W. Lin, Max Tegmark, and David Rolnick

We explore how properties frequently encountered in physics such as symmetry, locality, compositionality, and
polynomial log-probability translate into exceptionally simple neural networks

Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures