[14] Been Kim - Interactive and Interpretable Machine Learning Models
The Thesis Review
00:00
The Importance of Building Interpretable Models
For raw performance, you can choose some baseline and optimize towards that. But for interpretability, it's usually a lot more complicated. You have to look at specific applications. So it might make sense to develop these high-performance models and then do the black box interpretability methods that are driven by the applications.
Play episode from 40:30
Transcript
