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)
Is There Just More Pixles in the Visual Domain?
No pixa level reconstruction, right? If you were to do burt and just like, crop out or put random pixtles in, you have to like the alpo that to be this gigantic image. And that's how otto and coners workand they're just not as good. There are just more ways that you can diverge in the visual world but still be semetrically equivalent. Are there just infinitely more, infinite ways in the visual domain? Could youan linger on that a little bit more? I mean, i think i can express the same thing in so many different ways, but maybe it's just not as many as i could express the same
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