Keith Duggar + Tim Scarfe + Yannic Kilcher & Yann LeCun + Randall Balestriero , Machine Learning Street Talk (MLST)

061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)

04 Jan 2022 • 199 min • EN
199 min
No file found

We are now sponsored by Weights and Biases! Please visit our sponsor link: Patreon: Yann LeCun thinks that it's specious to say neural network models are interpolating because in high dimensions, everything is extrapolation. Recently Dr. Randall Balestriero, Dr. Jerome Pesente and prof. Yann LeCun released their paper learning in high dimensions always amounts to extrapolation. This discussion has completely changed how we think about neural networks and their behaviour. [00:00:00] Pre-intro [00:11:58] Intro Part 1: On linearisation in NNs [00:28:17] Intro Part 2: On interpolation in NNs [00:47:45] Intro Part 3: On the curse [00:48:19] LeCun [01:40:51] Randall B YouTube version:

From "Machine Learning Street Talk (MLST)"

Listen on your iPhone

Download our iOS app and listen to interviews anywhere. Enjoy all of the listener functions in one slick package. Why not give it a try?

App Store Logo
application screenshot

Popular categories