Explaining Deep Learning Models with Constrained Adversarial Examples
By J. Moore, Nils Y. Hammerla, Chris Watkins. 2019
45 citations recorded by the source corpus.
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decision to be made, and to give an informative explanation. We explore a new method of generating counterfactual explanations, which instead of explaining why a particular classification was made explain how a different outcome can be achieved. This gives the recipients of the explanation a better way to understand the outcome, and provides an actionable suggestion. We show that the introduced method of Constrained Adversarial Examples (CADEX) can be used in real world applications, and yields explanations which incorporate business or domain constraints such as handling categorical attributes and range constraints.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Martin Pereira-Fariña
- Ilia Stepin
- Alejandro Catalá
- J. Alonso
- Christian Walter Peter Omlin
- Waddah Saeed
Citations in the corpus
- A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “More precisely, ML-specific contfactual explanations are designed to answer the question: ‘‘Why was the outcome Y observed instead of Y ?’’ [148].”