2min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yann LeCun and Energy-Based Models

Machine Learning Street Talk (MLST)

CHAPTER

How to Find Points Off and on the Manifold of a Burt Model

With each pre training task, you're finding a different way of defining points off and on the manifold. So we've learned this language manifold, and with a burt model that takes in, let's say, 500 tokens. It's less than 500, because generally there's a separatedto but every single point on that manifold is a piece of valid language. i think it comes back to this idea of stepping stones and curriculum learning an that we have these different manifolds, alike substance of this high dimensional space.

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