Toward Design and Evaluation Framework for Interpretable Machine Learning Systems

Abstract

The need for interpretable and accountable intelligent system gets sensible as artificial intelligence plays more role in human life. Explainable artificial intelligence systems can be a solution by self-explaining the reasoning behind the decisions and predictions of the intelligent system. My research supports the design and evaluation methods and interpretable machine learning systems and leverages knowledge and experience in the fields of machine learning, human-computer interactions, and data visualization. My research objectives are to present a design and evaluation framework for explainable artificial intelligence systems, propose new methods and metrics to better evaluate the benefits of transparent machine learning systems, and apply interpretability methods for model reliability verification.