BI 052 Andrew Saxe: Deep Learning Theory

November 06, 2019 01:25:48
BI 052 Andrew Saxe: Deep Learning Theory
Brain Inspired
BI 052 Andrew Saxe: Deep Learning Theory

Nov 06 2019 | 01:25:48

/

Show Notes

Support the Podcast

Andrew and I discuss his work exploring how various facets of deep networks contribute to their function, i.e. deep network theory. We talk about what he’s learned by studying linear deep networks and asking how depth and initial weights affect learning dynamics, when replay is appropriate (and when it’s not), how semantics develop, and what it all might tell us about deep learning in brains.

Show notes:

A few recommended texts to dive deeper:

Other Episodes

Episode 0

January 29, 2021 01:34:10
Episode Cover

BI 096 Keisuke Fukuda and Josh Cosman: Forking Paths

K, Josh, and I were postdocs together in Jeff Schall’s and Geoff Woodman’s labs. K and Josh had backgrounds in psychology and were getting...

Listen

Episode 0

August 13, 2021 01:23:50
Episode Cover

BI NMA 05: NLP and Generative Models Panel

BI NMA 05: NLP and Generative Models Panel This is the 5th in a series of panel discussions in collaboration with Neuromatch Academy, the...

Listen

Episode 0

March 09, 2021 00:42:32
Episode Cover

BI 100.1 Special: What Has Improved Your Career or Well-being?

Brain Inspired turns 100 (episodes) today! To celebrate, my patreon supporters helped me create a list of questions to ask my previous guests, many...

Listen