Evolutionary approaches to explainable machine learning

Abstract

Machine learning models are increasingly being used in critical sectors, but their black-box nature has raised concerns about accountability and trust. The field of explainable artificial intelligence (XAI) or explainable machine learning (XML) has emerged in response to the need for human understanding of these models. Evolutionary computing, as a family of powerful optimization and learning tools, has significant potential to contribute to XAI/XML. In this chapter, we provide a brief introduction to XAI/XML and review various techniques in current use for explaining machine learning models. We then focus on how evolutionary computing can be used in XAI/XML, and review some approaches which incorporate EC techniques. We also discuss some open challenges in XAI/XML and opportunities for future research in this field using EC. Our aim is to demonstrate that evolutionary computing is well-suited for addressing current problems in explainability, and to encourage further exploration of these methods to contribute to the development of more transparent, trustworthy and accountable machine learning models.

References in corpus (11)

• Interpretable machine learning: definitions, methods, and applications
• One pixel attack for fooling deep neural networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Determinantal point processes for machine learning
• Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
• CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models
• Multi-Objective Counterfactual Explanations
• Multi-objective Feature Selection with Missing Data in Classification
• Genetic Programming for Evolving a Front of Interpretable Models for Data Visualisation
• On Explaining Machine Learning Models by Evolving Crucial and Compact Features

Cited by in corpus (1)

• Guiding the generation of counterfactual explanations through temporal background knowledge for Predictive Process Monitoring