2min chapter

Lex Fridman Podcast cover image

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

Lex Fridman Podcast

CHAPTER

How to Represent Knowledge as Symbols

Soth ts to be questioned. So, in your intuition is, if we look at expert systems and in coding knowledge as logic systems, as grafts, or in this kind of way, is not a useful way to think about knowledge. Grafts are a little brittle, or or logic a representation. Sobesically, you know, vibles thattha have value and and constrained between them, that are represented by woles a little too rigid and too brittle. Tis a very good set of ideas by a written in a paper about ten years ago by leon betou on,. who is here at fates work. The title of the paper is for machine learning to

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