Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?

Lerma, Miguel, Lucas, Mirtha

arXiv.org Artificial Intelligence 

Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of pre-softmax scores versus post-softmax scores, and their respective advantages and disadvantages.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found