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:
Mentioned in the show: Mark’s lab The excellent blog he writes on Medium The paper we discuss: An ensemble code in medial prefrontal cortex...
Show notes BLAM (Brain, Learning, Animation, and Movement) Lab homepage: http://blam-lab.org/ BLAM on Twitter: @blamlab Papers we discuss: Neuroscience Needs Behavior: Correcting a Reductionist...
Jon and I discuss understanding the syntax and semantics of language in our brains. He uses linguistic knowledge at the level of sentence and...