Search Results for author:
Found 2 papers, 2 papers with code
Maximizing Invariant Data Perturbation with Stochastic Optimization
Feature attribution methods, or saliency maps, are one of the most popular approaches for explaining the decisions of complex machine learning models such as deep neural networks.
Maximally Invariant Data Perturbation as Explanation
In adversarial example, one seeks the smallest data perturbation that changes the model's output.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
