Learning by Doing
Jeremy emphasizes his preference for hands-on learning, where he engages with research papers only to the point of identifying actionable ideas. He draws inspiration from Richard Feynman's approach, using physical analogies to deepen his understanding and spot potential errors in research. This intuitive and experimental mindset shapes his grasp of machine learning concepts.In this clip
From this podcast

Gradient Dissent - A Machine Learning Podcast
Jeremy Howard — The Story of fast.ai and Why Python Is Not the Future of ML
Related Questions