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

Miguel Lerma, Mirtha Lucas · 2023

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.

Read the paper · More papers on PaperTik