Lex Fridman Podcast cover image

Vladimir Vapnik: Statistical Learning

Lex Fridman Podcast

00:00

Deep Learning Is Not a Very Difficult Problem

A learning system that we don't, i think, mathematically understand that well, beats the best human player. The fact is, a ner novic system doesn't matter. And usually when people use deep learning, they're using zilions of training data. But you don't need this. So i describe challenge. Can we do some problems which do well deep lornic method? This dep net are using hundred times less tranin dad. Even more, some problems deep lornig cannot solve because it's not necessary. They create admissible set of function nli. To create deep architecture means to createadmissible set of functions. Youe just your fh

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