Explaining image classifiers using statistical fault localization
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for “Explainable AI”. In this paper, we show that statistical fault localization (SFL) techniques from software engineering deliver high quality explanations of...
Prif Awduron: | Sun, Y, Chockler, H, Huang, X, Kroening, D |
---|---|
Fformat: | Conference item |
Iaith: | English |
Cyhoeddwyd: |
Springer
2020
|
Eitemau Tebyg
-
Probabilistic fault localisation
gan: Landsberg, D, et al.
Cyhoeddwyd: (2016) -
Explainability and Transparency of Classifiers for Air-Handling Unit Faults Using Explainable Artificial Intelligence (XAI)
gan: Molika Meas, et al.
Cyhoeddwyd: (2022-08-01) -
Coverage in interpolation-based model checking
gan: Chockler, H, et al.
Cyhoeddwyd: (2010) -
Computing mutation coverage in interpolation-based model checking
gan: Chockler, H, et al.
Cyhoeddwyd: (2012) -
Optimising spectrum based fault localisation for single fault programs using specifications
gan: Landsberg, D, et al.
Cyhoeddwyd: (2018)