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)
What Do You Think Is a Better Definition of Interpolation?
There's a sense in which that's an extremely rigid definition of interpolation, rightandis. So i say it's a very task dependent. It will be really dependent on the type of task you are looking down don stream. I'd like to go back to what we were saying earlier on first trying to compress some of your data so that you can explain it with as little a factosa valation as possible. And then you can use the current definition just on compression of your data. Then it coll make sense er, because you don't really mind about the finike details of your objects if you just want to differentiate between different classes of objects. E, but in another setting
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