1min chapter

Lex Fridman Podcast cover image

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

Lex Fridman Podcast

CHAPTER

How Many Bullion Functions Are Therek?

So let's imagine you want to train your visual system. Two classification with one million binery inputs. How many such bullion functions are therek? You have two to the one million combinations of inputs. Bfor each of those, you have output bit. So we are ridiculously specialized. It's not at all yesi socialized. Yes, that specialization is still now pretty damn impressive. Is not perfect generalization. Is not even close. No, no, it's, it's,. it's its it's not that. The answer is an enormously tiny sliver.

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