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)
Using Sasupervision in Natural Language Programming
Energy functions have been used in vitous contexts or over the years, either for thing like tias networks of matric drowning. In denusing outo encorder, you train the system to map corrupted version to clean versions. And so you have automatically an energy surface that grows with the distance to the manifold. This represents the vect field of the is te gradient field of the energy function produced by in ortoin cod. So this is really interesting. I think a frequentist would still normalise their distributions, but it could maybe be compared ah into probablistic models.
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