Litcius/Paper detail

Robust Explainability: A tutorial on gradient-based attribution methods for deep neural networks

Ian E. Nielsen, Dimah Dera, Ghulam Rasool, Ravi P. Ramachandran, Nidhal Bouaynaya

2022IEEE Signal Processing Magazine105 citationsDOIOpen Access PDF

Abstract

The rise in deep neural networks (DNNs) has led to increased interest in explaining their predictions. While many methods for this exist, there is currently no consensus on how to evaluate them. On the other hand, robustness is a popular topic for deep learning (DL) research; however, it has been hardly talked about in explainability until very recently.

Topics & Concepts

InterpretabilityRobustness (evolution)Computer scienceArtificial intelligenceDeep neural networksDeep learningMachine learningArtificial neural networkGeneBiochemistryChemistryExplainable Artificial Intelligence (XAI)Adversarial Robustness in Machine LearningMachine Learning and Data Classification
Robust Explainability: A tutorial on gradient-based attribution methods for deep neural networks | Litcius