AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
Interporation in a Deep Neural Network
In the latin space, you have hundreds of dimensions, and you sample those guils from a guchan distribution. That lies in the interporation regime as soon asa dimensionality is greater tanlesssay, 15 or 20. Of course, if your ar generative, natoagjust a spits out a constant, then in picter space you will have interporation. But this is degenerated by definition. So we'll have to have a sort of flossy, a compression of othertyp and then you can try to wich ther with mare chances. i think you just steel manned the argument for interpolation so that what folks do, argue
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