061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
Revisiting High-Dimensional Neural Networks: Interpolation vs. Extrapolation
This chapter explores the intricate nature of neural networks and the challenges of high-dimensional statistical generalization. It highlights a recent paper that redefines concepts of interpolation and extrapolation, shedding light on how neural networks function and represent input predictions.
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.
