Actionable XAI for the Fuzzy Integral
Document Type
Conference Proceeding
Publication Date
8-5-2021
Department
Department of Computer Science
Abstract
The adoption of artificial intelligence (AI) into domains that impact human life (healthcare, agriculture, security and defense, etc.) has led to an increased demand for explainable AI (XAI). Herein, we focus on an under represented piece of the XAI puzzle, information fusion. To date, a number of low-level XAI explanation methods have been proposed for the fuzzy integral (FI). However, these explanations are tailored to experts and its not always clear what to do with the information they return. In this article we review and categorize existing FI work according to recent XAI nomenclature. Second, we identify a set of initial actions that a user can take in response to these low-level statistical, graphical, local, and linguistic XAI explanations. Third, we investigate the design of an interactive user friendly XAI report. Two case studies, one synthetic and one real, show the results of following recommended actions to understand and improve tasks involving classification.
Publication Title
IEEE International Conference on Fuzzy Systems
ISBN
9781665444071
Recommended Citation
Murray, B.,
Anderson, D.,
&
Havens, T. C.
(2021).
Actionable XAI for the Fuzzy Integral.
IEEE International Conference on Fuzzy Systems,
2021-July.
http://doi.org/10.1109/FUZZ45933.2021.9494563
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/15373