AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How Do We Learn Models of the World?
The main problem we need to solve is, how do we learn models of the world? That's and that's what self supervise running is all about. If you were to try to construct a bench mark for a, let's, let's look at amnes, i'd love that. The question is, what other type of learning are you alowed to do? So if what your allowed to do is train on some gigantic, dediset of labelled digit, that school transfer learning. And we know that worksk,. a we do this at fits book lik production, rightwe training large complechantes to predict hashtags that people type on instograham. You can