The Gradient: Perspectives on AI cover image

Been Kim: Interpretable Machine Learning

The Gradient: Perspectives on AI

00:00

The Interpretability Field Is Taking Similar Path

Michael: I think interpretability field is taking similar path where some people still argue well, we need a mathematical definition of what explanation is. And then we're now turning around and saying, actually, no, you can't. That's like fundamental science and philosophy that they talked about for centuries. He says there are different definitions of interpretability that might be a play. Michael: We just finished and published a chapter on Kevin Murphy's book, Probabilistic Machine Learning, a chapter on interpretability. Where we expend that list much, much longer.

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