Visible to the public Explainable AI for Understanding Decisions and Data-Driven Optimization of the Choquet Integral

TitleExplainable AI for Understanding Decisions and Data-Driven Optimization of the Choquet Integral
Publication TypeConference Paper
Year of Publication2018
AuthorsMurray, B., Islam, M. A., Pinar, A. J., Havens, T. C., Anderson, D. T., Scott, G.
Conference Name2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
Keywordsartificial intelligence, Choquet integral, convolution, convolutional neural networks, data-centric XAI tools, data-driven optimization, Electronic mail, explainable AI, feedforward neural nets, Frequency modulation, fusion solution, Fuzzy integral, heterogeneous deep convolutional neural networks, Indexes, learning (artificial intelligence), machine learning, optimisation, Optimization, parametric nonlinear aggregation function, pubcrawl, remote sensing, resilience, Resiliency, Scalability, sensor fusion, xai, XAI-ChI methods
AbstractTo date, numerous ways have been created to learn a fusion solution from data. However, a gap exists in terms of understanding the quality of what was learned and how trustworthy the fusion is for future-i.e., new-data. In part, the current paper is driven by the demand for so-called explainable AI (XAI). Herein, we discuss methods for XAI of the Choquet integral (ChI), a parametric nonlinear aggregation function. Specifically, we review existing indices, and we introduce new data-centric XAI tools. These various XAI-ChI methods are explored in the context of fusing a set of heterogeneous deep convolutional neural networks for remote sensing.
Citation Keymurray_explainable_2018