Published: October 24, 2020
Author(s)
Richard Kuhn (NIST), Raghu Kacker (NIST), Yu Lei (UTA), Dimitris Simos (SBA Research)
Conference
Name: IEEE International Conference on Software Testing Verification and Validation Workshop (ICSTW 2020)
Dates: 10/24/2020 - 10/28/2020
Location: [Virtual] Porto, Portugal
Citation: 2020 IEEE International Conference on Software Testing, Verification and Validation Workshop (ICSTW), pp. 167-170
This short paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually simple scheme to make it easy to justify classification decisions: identifying combinations of features that are present in members of the identified class and absent or rare in non-members. The method has been implemented in a prototype tool, and examples of its application are given.
This short paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually simple scheme to make it easy to justify...
See full abstract
This short paper introduces an approach to producing explanations or justifications of decisions made by artificial intelligence and machine learning (AI/ML) systems, using methods derived from fault location in combinatorial testing. We use a conceptually simple scheme to make it easy to justify classification decisions: identifying combinations of features that are present in members of the identified class and absent or rare in non-members. The method has been implemented in a prototype tool, and examples of its application are given.
Hide full abstract
Keywords
artificial intelligence; combinatorial testing; explainable AI; machine learning; t-way testing
Control Families
None selected
