The Importance of Interpretability in AI

There's a set of trade offs here that really have to be considered when we're deciding where to automate. For example, there was this article out of Stanford's human centered artificial intelligence institute some time back. ML has never lacked interpretability, only certain types of ML, lack higher degrees of interpretability. So there's this trade off and people are working on it. And they create opportunities for people who aren't just like computer scientists because you need to be close to the work.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.