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)
Is the Latent Too Big?
If the latent space is too big, lots of information will be incoded. And so even though it may be putting all kinds of little bits of extra information, it's probably only adding little plus or minus,. You know, point point one %, tight, tight things to the accuracy. Whereas andand so, since it is only adding these little, kind of very tiny values there, right? The only meaningful way to talk about interpolation or extrapolation on that entire dimension you've added there is really more just, are you interpolating ont the most salient dimensions?, he asks.
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