2 citations · 3 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2023★ 2 cited
Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?
Miguel Lerma, Mirtha Lucas
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…
cs.LG2023
A Vulnerability of Attribution Methods Using Pre-Softmax Scores
Miguel Lerma, Mirtha Lucas
We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is k…
cs.LG2021
Symmetry-Preserving Paths in Integrated Gradients
Miguel Lerma, Mirtha Lucas
We provide rigorous proofs that the Integrated Gradients (IG) attribution method for deep networks satisfies completeness and symmetry-preserving properties. We also study the uniq…