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:
Show notes: Websites: Ioana Marinescu, Konrad KordingTwitter: Twitter: @mioana; @KordingLabThe paper we discuss: Quasi-experimental causality in neuroscience and behavioral research.A Pre-print version. Judea Pearl’s...
Check out my free video series about what's missing in AI and Neuroscience Support the show to get full episodes and join the Discord...
Show notes: Visit Rafal’s Lab Website. Rafal’s papers we discuss: Theories of Error Back-Propagation in the Brain. An Approximation of the Error Backpropagation Algorithm...