AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
#64 Prof. Gary Marcus 3.0
Machine Learning Street Talk (MLST)
The Compositional Models of the Real World
Qouse: I think we're capable both of representing abstractions and concrete stuff. In particular, what's really driving it is creating symbolic representations of the parts that are intended to be stable across context. And i can't speak to the technical details ecause i haven't read the paper yet. Is it published yet? Just publishdi, i need to read the paper before i say too much. But i will say that the act characterization of what he's doing, i think, is both right and a step towards nero symbolic cognition. It's taking a play book that is very clearly understood in the symbolic world of constructing holes out of their parts. So you could imagine, for
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode