AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
ICLR 2020: Yann LeCun and Energy-Based Models
Machine Learning Street Talk (MLST)
Machine Learning - Energy Functions
This talk dives into the technical discuss of energy functions and how they construct the data manifold eonlyconis talk about very specific types of application here. We can formulate almost any machine learning problem in terms of an energy function. If you ever saw a deep dream or something like this, those models do exactly that. They optimize the input image for a particular label. And there you can view the entire neural network, including the loss function as the energy function. The three of us brothers struggle with grasping what yon lecan is and isn't talking about. So we're trying to make sense of pretty much all of machine learning one go. It's a bit of a different talk for us
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