Episode 12: Artificial Intelligence vs Artificial General Intelligence
The Theory of Anything
00:00
The Limits of Machine Learning
Each machine learning algorithm beyond having an inductive bias, it also has a hypothesis space. There is no theory how to explain how to come up with this set of hypothesis in the first place. And I think that's true of all machine learning today. We're getting better at letting the machine do more and more heavy lifting. But all of it is based on this really narrow concept of an inductive biases and a hypothesis space - narrowing it to a specific version space.
Transcript
Play full episode
