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)
How to Train Energy Functions as Models
We can build these energy functions that tell you ly how far you're away from the manifold. So if you can build an energy function like this, then at least you can hit the manifold with a reasonable probability by simply making the energy function happy. Co i wilbe the angle that leads to the point, the crossest point on that manifold. But in more complex cases, of course, we need to find this manifold, and the parent pysition is non trivial,. so how we train energy b as models? What we need to do is make sure the energy for deta samples is lower than the energy outside of the dee 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