061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
Redefining Interpolation in Deep Learning
This chapter discusses the need for a redefinition of interpolation as it applies to deep learning models, emphasizing the limitations of traditional interpretations. The speakers explore how dimensionality affects interpolation and extrapolation, particularly in the context of high-dimensional machine learning frameworks like GANs. They advocate for a more flexible understanding of these concepts tailored to specific tasks to enhance generalization and performance.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
