Lex Fridman Podcast cover image

Juergen Schmidhuber: Godel Machines, Meta-Learning, and LSTMs

Lex Fridman Podcast

00:00

The Future of Artificial Intelligence

It's very useful for a theory, improving thet there improvers to day are not your networks, right? No. They are largely programming systems. And they are much better ther improvers than most er math students in the first or second mester. It certainly has a usefulness in when you try to construct something provably obtimal or provably good, or something like that. But i's a useful forfor practical problems. You think learning, as long as the problems have little to do with with ther improving themselves, then as long as that is not the case, you just want to have better pattern recognition.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app