AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
Do You Need Latent, Virable Models?
The world is not completely predictable. It may be deterministic, but you don't have full observation. You cannot predict exactly what's going to happena in the world. So how do you deal with no certainty? And for that, you need predictive models that can represent uncertainty. We are back to the issue i wasta telling you about earlier. Ah, do you need latent, virable models, or gontebeding architectures? Right? That's and i've achanged my mind about this, as i told you. I think most problems are some combination of the two. But we have to realize that humans are really, really bad at the discreet exploration stuff. We totally
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