A user-based taxonomy for deep learning visualization

Deep learning has achieved impressive success in a variety of tasks and is developing rapidly in recent years. The problem of understanding the deep learning models has become an issue for the development of deep learning, for example, in domains like medicine and finance which require interpretable models. While it is challenging to analyze and interpret complicated deep neural networks, visualization is good at bridging between abstract data and intuitive representations. Visual analytics for deep learning is a rapidly growing research field. To help users better understand this field, we present a mini-survey including a user-based taxonomy that covers state-of-the-art works of the field. Regarding the requirements of different types of users (beginners, practitioners, developers, and experts), we categorize the methods and tools by four visualization goals respectively focusing on teaching deep learning concepts, architecture assessment, tools for debugging and improving models, and visual explanation. Notably, we present a table consisting of the name of the method or tool, the year, the visualization goal, and the types of networks to which the method or tool can be applied, to assist users in finding available tools and methods quickly. To emphasize the importance of visual explanation for deep learning, we introduce the studies in this research field in detail.