Evaluations and Methods for Explanation through Robustness Analysis

Hsieh Cheng-Yu
Hsieh Cheng-Yu
Yeh Chih-Kuan
Yeh Chih-Kuan
Kim Seungyeon
Kim Seungyeon
Kumar Sanjiv
Kumar Sanjiv
Cited by: 0|Bibtex|Views61|Links

Abstract:

Among multiple ways of interpreting a machine learning model, measuring the importance of a set of features tied to a prediction is probably one of the most intuitive ways to explain a model. In this paper, we establish the link between a set of features to a prediction with a new evaluation criterion, robustness analysis, which measure...More

Code:

Data:

Your rating :
0

 

Tags
Comments