Neural Network Predictions
Yann and Tim discuss using neural networks to predict multiple future scenarios in a model predictive control system. Yann emphasizes the importance of an energy function with multiple minima to explore different outcomes. The conversation delves into contrasting this method with reinforcement learning and its implications for driving cars autonomously.In this clip
From this podcast

Machine Learning Street Talk (MLST)
ICLR 2020: Yann LeCun and Energy-Based Models
Related Questions