Solving Complex Problems
François and Lex discuss the potential of deep learning in solving complex problems, including perception and natural language dialogue. They explore the limitations of deep learning and the importance of having a rich and flexible search space, as well as the challenges of formulating statements about the world. While deep learning is a great fit for perception problems, it may not be the most efficient solution for problems that require explicit handcrafted rules or reasoning about the physics of the scene.In this clip
From this podcast
Lex Fridman Podcast
François Chollet: Keras, Deep Learning, and the Progress of AI | Lex Fridman Podcast #38
Related Questions