Deep learning has recently seen rapid development and received significant attention due to its state-of-the-art performance on previously-thought hard problems. However, because of the internal complexity and nonlinear structure of deep neural networks, the underlying decision making processes for why these models are achieving such performance are challenging and sometimes mystifying to interpret. As deep learning spreads across domains, it is of paramount importance that we equip users of deep learning with tools for understanding when a model works correctly, when it fails, and ultimately how to improve its performance. Standardized toolkits for building neural networks have helped democratize deep learning; visual analytics systems have now been developed to support model explanation, interpretation, debugging, and improvement. We present a survey of the role of visual analytics in deep learning research, which highlights its short yet impactful history and thoroughly summarizes the state-of-the-art using a human-centered interrogative framework, focusing on the Five W's and How (Why, Who, What, How, When, and Where). We conclude by highlighting research directions and open research problems. This survey helps researchers and practitioners in both visual analytics and deep learning to quickly learn key aspects of this young and rapidly growing body of research, whose impact spans a diverse range of domains.

Fig. 1. ACTIVIS integrates several coordinated views to support exploration of complex deep neural network models, at both instanceand subset-level. 1. Our user Susan starts exploring the model architecture, through its computation graph overview (at A). Selecting a data node (in yellow) displays its neuron activations (at B). 2. The neuron activation matrix view shows the activations for instances and instance subsets; the projected view displays the 2-D projection of instance activations. 3. From the instance selection panel (at C), she explores individual instances and their classification results. 4. Adding instances to the matrix view enables comparison of activation patterns across instances, subsets, and classes, revealing causes for misclassification.Abstract-While deep learning models have achieved state-of-the-art accuracies for many prediction tasks, understanding these models remains a challenge. Despite the recent interest in developing visual tools to help users interpret deep learning models, the complexity and wide variety of models deployed in industry, and the large-scale datasets that they used, pose unique design challenges that are inadequately addressed by existing work. Through participatory design sessions with over 15 researchers and engineers at Facebook, we have developed, deployed, and iteratively improved ACTIVIS, an interactive visualization system for interpreting large-scale deep learning models and results. By tightly integrating multiple coordinated views, such as a computation graph overview of the model architecture, and a neuron activation view for pattern discovery and comparison, users can explore complex deep neural network models at both the instance-and subset-level. ACTIVIS has been deployed on Facebook's machine learning platform. We present case studies with Facebook researchers and engineers, and usage scenarios of how ACTIVIS may work with different models.

Recent success in deep learning has generated immense interest among practitioners and students, inspiring many to learn about this new technology. While visual and interactive approaches have been successfully developed to help people more easily learn deep learning, most existing tools focus on simpler models. In this work, we present GAN Lab, the first interactive visualization tool designed for non-experts to learn and experiment with Generative Adversarial Networks (GANs), a popular class of complex deep learning models. With GAN Lab, users can interactively train generative models and visualize the dynamic training process's intermediate results. GAN Lab tightly integrates an model overview graph that summarizes GAN's structure, and a layered distributions view that helps users interpret the interplay between submodels. GAN Lab introduces new interactive experimentation features for learning complex deep learning models, such as step-by-step training at multiple levels of abstraction for understanding intricate training dynamics. Implemented using TensorFlow.js, GAN Lab is accessible to anyone via modern web browsers, without the need for installation or specialized hardware, overcoming a major practical challenge in deploying interactive tools for deep learning.

African-American Male subgroup Detailed comparison of the groups Caucasian Male and African-American Male Figure 1: FAIRVIS integrates multiple coordinated views for discovering intersectional bias. Above, our user investigates the intersectional subgroups of sex and race. A. The Feature Distribution View allows users to visualize each feature's distribution and generate subgroups. B. The Subgroup Overview lets users select various fairness metrics to see the global average per metric and compare subgroups to one another, e.g., pinned Caucasian Males versus hovered African-American Males. The plots for Recall and False Positive Rate show that for African-American Males, the model has relatively high recall but also the highest false positive rate out of all subgroups of sex and race. C. The Detailed Comparison View lets users compare the details of two groups and investigate their class balances. Since the difference in False Positive Rates between Caucasian Males and African-American Males is far larger than their difference in base rates, a user suspects this part of the model merits further inquiry. D. The Suggested and Similar Subgroup View shows suggested subgroups ranked by the worst performance in a given metric.