Visual Analytics for Explainable Deep Learning
This is an incremental review paper that discusses challenges and future directions for improving explainability in deep learning, targeting researchers and practitioners in AI and visual analytics.
The paper addresses the problem of deep learning models lacking explainability and control in critical applications like precision medicine and law enforcement, by reviewing visual analytics, information visualization, and machine learning perspectives to make these models more interpretable and controllable.
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. In this paper, we review visual analytics, information visualization, and machine learning perspectives relevant to this aim, and discuss potential challenges and future research directions.