In-Distribution Interpretability for Challenging Modalities

Cosmas Heiß
Cosmas Heiß
Ron Levie
Ron Levie
Cinjon Resnick
Cinjon Resnick
Cited by: 0|Bibtex|Views8|Links

Abstract:

It is widely recognized that the predictions of deep neural networks are difficult to parse relative to simpler approaches. However, the development of methods to investigate the mode of operation of such models has advanced rapidly in the past few years. Recent work introduced an intuitive framework which utilizes generative models to ...More

Code:

Data:

Your rating :
0

 

Tags
Comments