Google’s ‘Nested Learning’ paradigm could solve AI's memory and continual learning problem

Inspired by how the human brain consolidates memory, the 'Nested Learning' framework allows different parts of a model to ...
Scientific Research Publishing

Covariant-Scale: Riemannian Manifold Learning for Scale-Invariant Video Anomaly Detection ()

Video-Based Anomaly Detection, Urban Surveillance, Scale-Projective Ambiguity, Riemannian Manifold, Scale-Covariant Tracking, ...
The Stanford ReviewOpinion

We Trained China’s AI Researchers. Now We Risk Being Surpassed in AI Innovation.

Reinforcement Learning, one of the year’s most popular classes, taught by Professor Chelsea Finn. Her lab revolutionized ...