Explainable AI (XAI)

Confronting Bias, Discrimination, and Fairness in Machine Learning

Abstract

Explainable AI (XAI) is a set of techniques and strategies to address the complexity and opacity of machine learning (ML) which can lead to predictions that promulgate bias, discrimination, and unfairness. The prevalence of ML-based library tools and resources underscores the importance of appropriately and effectively utilizing XAI.