3min snip

Lex Fridman Podcast cover image

#258 – Yann LeCun: Dark Matter of Intelligence and Self-Supervised Learning

Lex Fridman Podcast

NOTE

How to Avoid Collapse?

In contrastive running, you show two different images of the same object. You then train a network to produce an output representation e vactor a in such a way that those two images are as close to each other as possible. The idea was proposed by people at Belldabs and genbomley back in the early nineties. They were interested in storing a representation of the signature on 80 bites of the magnetic trip of a cretic card.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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