AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
ICLR 2020: Yann LeCun and Energy-Based Models
Machine Learning Street Talk (MLST)
How Far Is Too Far?
The perils of deep learning are that the models interpolate, they don't extrapolate. If you make a depression in the manifold, what you want is lots on of depressions in the manifold to form a canyon around your around where you want your manifold to be. But if the depressions are small and they don't form a nice canyon around your manifold, then you're not really learning anything about your manifold. So i an what i can do as it can form that valley between the what's truly in the language and these corrupted inputs. And we're just kind of hoping that that's enough. We don't consider any gibberish or anything. Yes, as you said
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