Recent advancements in machine learning and signal processing domains have resulted in an extensive surge of interest in Deep Neural Networks (DNNs) due to their unprecedented performance and high accuracy for different and challenging problems of significant engineering importance. However, when such deep learning architectures are utilized for making critical decisions such as the ones that involve human lives (e.g., in control systems and medical applications), it is of paramount importance to understand, trust, and in one word "explain" the argument behind deep models' decisions. In many applications, artificial neural networks (including DNNs) are considered as black-box systems, which do not provide sufficient clue on their internal processing actions. Although some recent efforts have been initiated to explain the behaviors and decisions of deep networks, explainable artificial intelligence (XAI) domain, which aims at reasoning about the behavior and decisions of DNNs, is still in its infancy. The aim of this paper is to provide a comprehensive overview on Understanding, Visualization, and Explanation of the internal and overall behavior of DNNs.
A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations
University of Maine（缅因大学）；University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Duke University（杜克大学）；University of Rochester（罗切斯特大学）；University of Iowa（爱荷华大学）
Multivariate Data Explanation by Jumping Emerging Patterns Visualization
Federal Institute of São Paulo（圣保罗联邦学院）；University of São Paulo（圣保罗大学）；Eindhoven University of Technology（埃因霍温理工大学）
可视化分析（VA）工具和技术在支持用户构建更好的分类模型、解释模型的整体逻辑和审计结果方面发挥了重要作用。在另一个方向，VA最近被应用于将分类模型转换为描述性机制而不是预测性机制。我们的想法是使用这样的模型作为数据模式的代理，可视化模型以理解数据所代表的现象。虽然非常有用和鼓舞人心的，少数提出的方法选择使用低复杂度的分类模型，以促进简单的解释，提出了限制捕捉复杂的数据模式。在本文中，我们提出了VAX（multiVariate dAta eXplanation），一种新的VA方法，以支持识别和视觉解释的模式在多元数据集。与现有的类似方法不同，VAX使用跳跃新兴模式的概念来识别和聚合多个多样化的模式，通过数据变量的逻辑组合产生解释。VAX解释复杂多元数据集的潜力通过使用两个涵盖不同场景的真实世界数据集的用例来证明。
Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization
Norwegian University of Science and Technology（挪威科技大学）；Department of Engineering Cybernetics, Norwegian University of Science and Technology（挪威科技大学工程控制论系）；Department of Design, Norwegian University of Science and Technology（挪威科技大学设计系）；Centre for Autonomous Marine Operations and Systems, Norwegian University of Science and Technology（挪威科技大学自主海洋操作与系统中心）
Manipulating Feature Visualizations with Gradient Slingshots
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；UMI Lab, ATB Potsdam（UMI实验室，ATB波茨坦）；University of Potsdam（波茨坦大学）；BIFOLD（BIFOLD机构）；Machine Learning and Security Group, TU Berlin（柏林技术大学机器学习与安全小组）；Machine Learning Group, TU Berlin（柏林技术大学机器学习小组）；Department of Artificial Intelligence, Korea University（韩国大学人工智能系）；Max-Planck Institute for Informatics（马克斯·普朗克信息研究所）；Centre of eXplainable Artificial Intelligence, TU Dublin（都柏林技术大学可解释人工智能中心）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心（MCML））；TU Munich（慕尼黑技术大学）
Analysis and Visualization of Deep Neural Networks in Device-Free Wi-Fi Indoor Localization
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Institute of Electronics, National Chiao Tung University（国立交通大学电子研究所）
User Perception of Attention Visualizations: Effects on Interpretability Across Evidence-Based Medical Documents
CENIA – Centro Nacional de Inteligencia Artificial（CENIA – 国家人工智能中心）；Pontificia Universidad Católica de Chile（天主教大学）；University of Pittsburgh（匹兹堡大学）；KU Leuven（根特大学）
A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures
Griffith University（格里菲斯大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；University of Bremen（不来梅大学）；Hanoi University of Science and Technology（河内科技大学）；The University of Queensland（昆士兰大学）
The Cultural Mapping and Pattern Analysis (CMAP) Visualization Toolkit: Open Source Text Analysis for Qualitative and Computational Social Science
Department of Sociology, Rice University（理海大学社会学系）；Rice University（理海大学）；Computational Ethnography Lab, Rice University（理海大学计算人类学实验室）；Center for Computational Insights on Inequality and Society (CIISR), Rice University（社会不平等与社会洞察中心（CIISR），理海大学）；Institute of Health Resilience and Innovation (IHRI), Rice University（健康韧性与创新研究所（IHRI），理海大学）；Ken Kennedy Institute (Responsible AI and Scientific Computing), Rice University（肯尼迪研究所（负责任的人工智能与科学计算），理海大学）；University of California San Francisco（旧金山大学）；University of California Berkeley（伯克利大学）
