English

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

Machine Learning 2023-07-20 v2 Artificial Intelligence

Abstract

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.

Cite

@article{arxiv.2306.13197,
  title  = {Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?},
  author = {Miguel Lerma and Mirtha Lucas},
  journal= {arXiv preprint arXiv:2306.13197},
  year   = {2023}
}

Comments

8 pages, 2 figures, 2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)

R2 v1 2026-06-28T11:12:22.562Z