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

2022-01-04 · 200 min · episode 61 · 5 entities

episode page audio

Asserted relationships

→ discusses Technology company

0.40

evidence rules-v4
Feed category: Technology
→ references Mlst website

0.38

evidence rules-v4
Link in episode "061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)": http://wandb.me/MLST

Entities found in this episode

companys 2

mentioned Technology company

0.50

evidence rules-v4
Feed category: Technology
discusses Technology company

0.40

evidence rules-v4
Feed category: Technology

websites 2

mentioned Mlst website

0.45

evidence rules-v4
Link in episode "061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)": http://wandb.me/MLST
references Mlst website

0.38

evidence rules-v4
Link in episode "061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)": http://wandb.me/MLST

podcasts 1

mentioned Machine Learning Street Talk (MLST podcast

0.95

evidence rules-v4
Feed title: Machine Learning Street Talk (MLST)

Episode description as stored

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