061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Media Type |
audio
Categories Via RSS |
Technology
Publication Date |
Jan 04, 2022
Episode Duration |
03:19:43

We are now sponsored by Weights and Biases! Please visit our sponsor link: http://wandb.me/MLST

Patreon: https://www.patreon.com/mlst

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: https://youtu.be/86ib0sfdFtw

This episode currently has no reviews.

Submit Review
This episode could use a review!

This episode could use a review! Have anything to say about it? Share your thoughts using the button below.

Submit Review