Visual Analytics for Explainable Deep Learning

• Published in: IEEE computer graphics and applications Vol. 38; no. 4; pp. 84 - 92
• Main Authors: Choo, Jaegul, Liu, Shixia
• Format: Magazine Article
• Language: English
• Published: United States IEEE 01.07.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytics; Artificial intelligence; Computational modeling; computer graphics; Data visualization; Decision making; Deep learning; explainable deep learning; interactive visualization; Law enforcement; Machine learning; Predictive models; Scientific visualization; Stability; Visual analytics
• ISSN: 0272-1716; 1558-1756; 1558-1756
• DOI: 10.1109/MCG.2018.042731661

Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of explanation regarding the decisions made by deep learning models and absence of control over their internal processes act as major drawbacks in critical decision-making processes, such as precision medicine and law enforcement. In response, efforts are being made to make deep learning interpretable and controllable by humans. This article reviews visual analytics, information visualization, and machine learning perspectives relevant to this aim, and discusses potential challenges and future research directions.