PodParley PodParley

#64 Prof. Gary Marcus 3.0

Episode 64 of the Machine Learning Street Talk (MLST) podcast, hosted by Machine Learning Street Talk (MLST), titled "#64 Prof. Gary Marcus 3.0" was published on February 24, 2022 and runs 51 minutes.

February 24, 2022 ·51m · Machine Learning Street Talk (MLST)

0:00 / 0:00

Patreon: https://www.patreon.com/mlst Discord: https://discord.gg/HNnAwSduud YT: https://www.youtube.com/watch?v=ZDY2nhkPZxw We have a chat with Prof. Gary Marcus about everything which is currently top of mind for him, consciousness  [00:00:00] Gary intro [00:01:25] Slightly conscious [00:24:59] Abstract, compositional models [00:32:46] Spline theory of NNs [00:36:17] Self driving cars / algebraic reasoning  [00:39:43] Extrapolation [00:44:15] Scaling laws [00:49:50] Maximum likelihood estimation References: Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets https://arxiv.org/abs/2201.02177 DEEP DOUBLE DESCENT: WHERE BIGGER MODELS AND MORE DATA HURT https://arxiv.org/pdf/1912.02292.pdf Bayesian Deep Learning and a Probabilistic Perspective of Generalization https://arxiv.org/pdf/2002.08791.pdf

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

Discord: https://discord.gg/HNnAwSduud

YT: https://www.youtube.com/watch?v=ZDY2nhkPZxw

We have a chat with Prof. Gary Marcus about everything which is currently top of mind for him, consciousness 


[00:00:00] Gary intro

[00:01:25] Slightly conscious

[00:24:59] Abstract, compositional models

[00:32:46] Spline theory of NNs

[00:36:17] Self driving cars / algebraic reasoning 

[00:39:43] Extrapolation

[00:44:15] Scaling laws

[00:49:50] Maximum likelihood estimation


References:

Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

https://arxiv.org/abs/2201.02177


DEEP DOUBLE DESCENT: WHERE BIGGER MODELS AND MORE DATA HURT

https://arxiv.org/pdf/1912.02292.pdf


Bayesian Deep Learning and a Probabilistic Perspective of Generalization

https://arxiv.org/pdf/2002.08791.pdf

No similar episodes found.

URL copied to clipboard!