AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
6min chapter
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
What's the Biggest Disagreement Between the Community and Nera Net?
The first paper on this was in 19 91, by my friend obeto and saviloncour. They were trying to do speech recognition. You can back properlyet gradi ont to a lot of different moduls. What those things do is that they infer alaten variable. Find the short of spats in a graph is a form of e energy mnimisationa. And so you can have, in a deep running system, you can have a modul that has rit an variable. This module will do is i figure out a value of the writ en varable that minimizes,. inimizes some energy function. Could be a prediction error, it could be
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