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 the Decotor and Predictor Model to Make the Energy Low
In this case, your learning your predictor and decota function to make the energy low. Well, if the decoter has predicted that exact thing on the manifold, then the loss will be zero. So its like wee injecttes rlike hereis how you can throw points off the manifold. And then i guess what's really bothering me with thinking about this is how it is mapped into this manifold because you're training the features as you're simultaneously, like talking about, pushing it off this manifold.
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