3min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yann LeCun and Energy-Based Models

Machine Learning Street Talk (MLST)

CHAPTER

Deep Learning Is Akin to a Linear Classifier

Deep learning is a little bit like imagine have a piece of paper that's been scrunched up into a ball. Ultimately, if you unfold all this through your neural network, and then you make a linear cut, which is what the supervised methods we have nowadays do. At the end, the data manifold,. so to say, is when you trace that cut backwards through all the layers, through this folding, and look at it in the input space. That's, that's basically what your neural network learns is whatever that cuts going to end op being in the inputspacei exactly.

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