AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
ICLR 2020: Yann LeCun and Energy-Based Models
Machine Learning Street Talk (MLST)
Learning to Use Logic Can't Make Into a Differential Loss Function
It's quite difficult to wrestle with because, in a sense, he deep lining models do reas they are analogous to computer programmes. I think this is really just a human concept and kind of a description of eof what he thinks these systems should be able to do in the future. People say it's a i if we don't understand it. Well, si, learning to use logic can't made into a differentiale loss function. But no one has done it very successfully so far.
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