2min chapter

Machine Learning Street Talk (MLST) cover image

#56 - Dr. Walid Saba, Gadi Singer, Prof. J. Mark Bishop (Panel discussion)

Machine Learning Street Talk (MLST)

CHAPTER

The Self Supervised Image Representation

There's a really strong argument, i think, that intelligence is generalization. When you look at some of the self supervised image representation learning our grithms flying round at the moment, they do seem to do exactly that. They learn a universal, monolitic vector representation that seems to make sense in a lod of situations. And face books ar the argument that because these things are self supervised, rather than having some pointalistic, human annotated label, it's harder to take a short cut. But as you just said, mark, those categories are probably not universal. I don't see wherer really the hope comes from, the idea that just letting it be self supervised

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