Events

Ten years into the revival of deep networks and artificial intelligence, we propose a theoretical framework that sheds light on understanding deep networks within a bigger picture of intelligence in general. We introduce two fundamental principles, Parsimony and Self-consistency, that address two fundamental questions regarding Intelligence: what to learn and how to learn, respectively. We […]

This talk will begin by discussing phase transitions in high-dimensional statistical inference problems. Some effort will be made to distinguish between problems with random structure (e.g., random codes and sparse PCA) and problems with deterministic structure (e.g., highly symmetric codes such as Reed-Muller codes). For problems with deterministic structure, we will observe that symmetry can […]