- author = "Ryan Zhou and Jaume Bacardit and Alexander Edward Ian Brownlee and Stefano Cagnoni and Martin Fyvie and Giovanni Iacca and John McCall and Niki {van Stein} and David Walker and Ting Hu",
- title = "Evolutionary Computation and Explainable {AI}: A Roadmap to Understandable Intelligent Systems",
- journal = "IEEE Transactions on Evolutionary Computation",
- year = "2025",
- volume = "29",
- number = "5",
- pages = "2213--2228",
- month = oct,
- keywords = "genetic algorithms, genetic programming, Artificial intelligence, XAI, Complexity theory, Optimization, Predictive models, Decision making, Data models, Measurement, Computational modeling, Numerical models, Machine learning algorithms, Evolutionary computation, EC, explainability, interpretability, machine learning, ML",
- ISSN = "1089-778X",
-
URL = "
https://arxiv.org/abs/2406.07811",
-
DOI = "
10.1109/TEVC.2024.3476443",
- 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 article provides an introduction to XAI and reviews current techniques for explaining machine learning (ML) 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 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.",
-
notes = "also known as \cite{10730793}
Some mentions of GP",
