Energy Functions vs. Probabilistic Models
Yann, Tim, Yannic, and Connor discuss the limitations of estimating densities using maximum likelihood in probabilistic models, leading to the creation of deep, narrow canyons. They explore the idea of using energy functions instead of probabilistic frameworks to learn dependencies more effectively.In this clip
From this podcast
Machine Learning Street Talk (MLST)
ICLR 2020: Yann LeCun and Energy-Based Models
Related Questions