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

October 11, 2018 00:52:27
Episode Cover

BI 013 Dileep George: Vicarious Robot AI

  Dileep’s homepage. Dileep on Twitter: @dileeplearning Vicarious, the general AI robotics company Dileep cofounded. Vicarious on Twitter: @vicariousai. The papers we discuss: A generative...

Listen

Episode 0

November 29, 2018 01:09:04
Episode Cover

BI 020 Anna Wexler: Stimulate Your Brain?

Show notes: Anna’s website: annawexler.com. Follow Anna on Twitter: @anna_wexler. Check out her documentary Unorthodox. The papers we discuss: Recurrent themes in the history...

Listen

Episode 0

December 15, 2020 01:42:12
Episode Cover

BI 092 Russ Poldrack: Cognitive Ontologies

Russ and I discuss cognitive ontologies - the "parts" of the mind and their relations - as an ongoing dilemma of how to map...

Listen