Uncertainty in Learning
Yann discusses the challenges of handling uncertainty in predictive models, emphasizing that real-world unpredictability complicates planning. He highlights the potential of active learning, where systems seek human input to improve their understanding and exploration, drawing parallels to how robots and infants learn from their environments. This approach could enhance the effectiveness of machine learning in dynamic settings.In this clip
From this podcast
Lex Fridman Podcast
Yann LeCun: Deep Learning, ConvNets, and Self-Supervised Learning | Lex Fridman Podcast #36
Related Questions