Evolutionary computation and explainable AI: a roadmap to understandable intelligent systems.

Zhou, Ryan; Bacardit, Jaume; Brownlee, Alexander E.I.; Cagnoni, Stefano; Fyvie, Martin; Iacca, Giovanni; McCall, John; van Stein, Niki; Walker, David J.; Hu, Ting

Abstract

Artificial intelligence methods are being increasingly applied across various domains, but their often opaque nature has raised concerns about accountability and trust. In response, the field of explainable AI (XAI) has emerged to address the need for human-understandable AI systems. Evolutionary computation (EC), a family of powerful optimization and learning algorithms, offers significant potential to contribute to XAI, and vice versa. This paper provides an introduction to XAI and reviews current techniques for explaining machine learning models. We then explore how EC can be leveraged in XAI and examine existing XAI approaches that incorporate EC techniques. Furthermore, we discuss the application of XAI principles within EC itself, investigating how these principles can illuminate the behavior and outcomes of EC algorithms, their (automatic) configuration, and the underlying problem landscapes they optimize. Finally, we discuss open challenges in XAI and highlight opportunities for future research at the intersection of XAI and EC. Our goal is to demonstrate EC's suitability for addressing current explainability challenges and to encourage further exploration of these methods, ultimately contributing to the development of more understandable and trustworthy ML models and EC algorithms.

Citation

ZHOU, R., BACARDIT, J., BROWNLEE, A.E.I., CAGNONI, S., FYVIE, M., IACCA, G., MCCALL, J., VAN STEIN, N., WALKER, D.J. and HU, T. [2024]. Evolutionary computation and explainable AI: a roadmap to understandable intelligent systems. IEEE Transactions on evolutionary computation [online], Early Access. Available from: https://doi.org/10.1109/TEVC.2024.3476443

• Journal Article Type: Article
• Acceptance Date: Sep 30, 2024
• Online Publication Date: Oct 23, 2024
• Deposit Date: Sep 30, 2024
• Publicly Available Date: Oct 29, 2024
• Journal: IEEE Transactions on evolutionary computation
• Print ISSN: 1089-778X
• Electronic ISSN: 1941-0026
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Peer Reviewed: Peer Reviewed
• DOI: https://doi.org/10.1109/tevc.2024.3476443
• Keywords: Explainability; Interpretability; Evolutionary computation; Machine learning
• Public URL: https://rgu-repository.worktribe.com/output/2492710