2min chapter

Lex Fridman Podcast cover image

Yann LeCun: Deep Learning, Convolutional Neural Networks, and Self-Supervised Learning

Lex Fridman Podcast

CHAPTER

Are You Using Self Supervised Learning to Make Things More Efficient?

I see self supervisring as as a preliminary to all of the above. To learn to play at harry games take about 80 hours of training to reach the level that any human can reach in about 15 minutes. They get better than humans, but it takes them a long time. Alfastar ok te, you know arriol vinas an, and is teams e system to play, to to play stock craft plays with about the eqivalment of 200 years of training, playing against itself. The e quickly explodes, what are your thoughts? And the extension of this, which topic i'm super excited about. Its connected to something you are talking about in terms of rabotics

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