[14] Been Kim - Interactive and Interpretable Machine Learning Models
The Thesis Review
00:00
How to Improve a Model to Be More Interpretable
Do you think that instead of being driven by applications, it's possible to just think about like, okay, how can we improve maybe a model better? And then when people in practice see that this model has this interpretable property, then that might actually open up new applications. Does that actually ever happen or is that just a wishful thinking? When you say applications, do you mean like new like business, like new, what would that look like? Yeah, that is a good question. You know, I think it is possible now I think about now I hear in your examples, totally.
Play episode from 34:57
Transcript
