Episode 58: Deutsch's "Creative Blocks": A Decade Later
The Theory of Anything
00:00
The Importance of Induction in Machine Learning
There's a whole branch of machine learning called explanation-based learning, where they've tried to model the concept of an explanation. And it actually has a lot of the qualities that we would expect of scientific explanations. But in fact, it's not even as good a form of machine learning today as regular neural nets that just use inductive probabilistic approaches. Why is that? That's a totally fair question. It's got nothing to do with a love of the philosophy of induction. The human brain clearly does more than that and our universal explainer ship is not rooted in it.
Transcript
Play full episode
