Machine Learning Challenges
Tim discusses the challenges of dimensionality and extrapolation in machine learning, emphasizing the importance of knowing what to ignore in input space and the implications of extrapolation on generalization in deep learning. He highlights the role of domain knowledge in neural networks and the significance of developer-aware generalization for model success.In this clip
From this podcast
Machine Learning Street Talk (MLST)
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Related Questions