Explainable Human Ai Interaction

From its inception, artificial intelligence (AI) has had a rather ambivalent relationship with humans—swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever-increasing pace, there is a greater need for AI systems to work synergistically with humans. One critical requirement for such synergistic human‒AI interaction is that the AI systems' behavior be explainable to the humans in the loop. To do this effectively, AI agents need to go beyond planning with their own models of the world, and take into account the mental model of the human in the loop. At a minimum, AI agents need approximations of the human's task and goal models, as well as the human's model of the AI agent's task and goal models. The former will guide the agent to anticipate and manage the needs, desires and attention of the humans in the loop, and the latter allow it to act in ways that are interpretable to humans (by conforming to their mental models of it), and be ready to provide customized explanations when needed. The authors draw from several years of research in their lab to discuss how an AI agent can use these mental models to either conform to human expectations or change those expectations through explanatory communication. While the focus of the book is on cooperative scenarios, it also covers how the same mental models can be used for obfuscation and deception. The book also describes several real-world application systems for collaborative decision-making that are based on the framework and techniques developed here. Although primarily driven by the authors' own research in these areas, every chapter will provide ample connections to relevant research from the wider literature. The technical topics covered in the book are self-contained and are accessible to readers with a basic background in AI.

The three-volume set CCIS 1032, CCIS 1033, and CCIS 1034 contains the extended abstracts of the posters presented during the 21st International Conference on Human-Computer Interaction, HCII 2019, which took place in Orlando, Florida, in July 2019.The total of 1274 papers and 209 posters included in the 35 HCII 2019 proceedings volumes was carefully reviewed and selected from 5029 submissions. The 208 papers presented in these three volumes are organized in topical sections as follows: Part I: design, development and evaluation methods and technique; multimodal Interaction; security and trust; accessibility and universal access; design and user experience case studies. Part II:interacting with games; human robot interaction; AI and machine learning in HCI; physiological measuring; object, motion and activity recognition; virtual and augmented reality; intelligent interactive environments. Part III: new trends in social media; HCI in business; learning technologies; HCI in transport and autonomous driving; HCI for health and well-being.

With an evolutionary advancement of Machine Learning (ML) algorithms, a rapid increase of data volumes and a significant improvement of computation powers, machine learning becomes hot in different applications. However, because of the nature of “black-box” in ML methods, ML still needs to be interpreted to link human and machine learning for transparency and user acceptance of delivered solutions. This edited book addresses such links from the perspectives of visualisation, explanation, trustworthiness and transparency. The book establishes the link between human and machine learning by exploring transparency in machine learning, visual explanation of ML processes, algorithmic explanation of ML models, human cognitive responses in ML-based decision making, human evaluation of machine learning and domain knowledge in transparent ML applications. This is the first book of its kind to systematically understand the current active research activities and outcomes related to human and machine learning. The book will not only inspire researchers to passionately develop new algorithms incorporating human for human-centred ML algorithms, resulting in the overall advancement of ML, but also help ML practitioners proactively use ML outputs for informative and trustworthy decision making. This book is intended for researchers and practitioners involved with machine learning and its applications. The book will especially benefit researchers in areas like artificial intelligence, decision support systems and human-computer interaction.

This edited book explores the many interesting questions that lie at the intersection between AI and HCI. It covers a comprehensive set of perspectives, methods and projects that present the challenges and opportunities that modern AI methods bring to HCI researchers and practitioners. The chapters take a clear departure from traditional HCI methods and leverage data-driven and deep learning methods to tackle HCI problems that were previously challenging or impossible to address. It starts with addressing classic HCI topics, including human behaviour modeling and input, and then dedicates a section to data and tools, two technical pillars of modern AI methods. These chapters exemplify how state-of-the-art deep learning methods infuse new directions and allow researchers to tackle long standing and newly emerging HCI problems alike. Artificial Intelligence for Human Computer Interaction: A Modern Approach concludes with a section on Specific Domains which covers a set of emerging HCI areas where modern AI methods start to show real impact, such as personalized medical, design, and UI automation.

This book constitutes the refereed proceedings of the First International Conference on Artificial Intelligence in HCI, AI-HCI 2020, held as part of the 22nd International Conference on Human-Computer Interaction, HCII 2020, in July 2020. The conference was planned to be held in Copenhagen, Denmark, but had to change to a virtual conference mode due to the COVID-19 pandemic. The conference presents results from academic and industrial research, as well as industrial experiences, on the use of Artificial Intelligence technologies to enhance Human-Computer Interaction. From a total of 6326 submissions, a total of 1439 papers and 238 posters has been accepted for publication in the HCII 2020 proceedings. The 30 papers presented in this volume were organized in topical sections as follows: Human-Centered AI; and AI Applications in HCI.pical sections as follows: Human-Centered AI; and AI Applications in HCI.

Advancements in deep learning have revolutionized AI systems, enabling collaboration between humans and AI to enhance performance in specific tasks. AI explanations play a crucial role in aiding human understanding, control, and improvement of AI systems regarding various criteria such as fairness, safety, and trustworthiness. Despite the proliferation of eXplainable AI (XAI) approaches, the practical usefulness of AI explanations in human-AI collaborative systems remains underexplored. This doctoral research aims to evaluate and enhance the usefulness of AI explanations for humans in practical human-AI collaboration. I break down the research goal of investigating and improving human-centered useful AI explanations into three research questions: RQ1: Are cutting-edge AI explanations useful for humans in practice (Part I)? RQ2: What's the disparity between AI explanations and practical user demands (Part II)? RQ3: How to empower useful AI explanations with human-AI interaction (Part III)? We examined the three research questions by conducting four projects. To answer RQ1, we deployed two real-world human evaluation studies on analyzing computer vision AI model errors with post-hoc explanations and simulating NLP AI model predictions with inherent explanations, respectively. The two studies unveil that, surprisingly, AI explanations are not always useful for humans to analyze AI predictions in practice. This motivates our research for RQ2 -- gaining insights into disparities between the status quo of AI explanations and practical user needs. By surveying over 200 AI explanation papers and comparing with summarized real-world user demands, we observe two dominating findings: i) humans request diverse XAI questions across the AI pipeline to gain a global view of AI system, whereas existing XAI approaches commonly display a single AI explanation that can not satisfy diverse XAI user needs; ii) humans are widely interested in understanding what AI systems can not achieve, which might lead to the need of interactive AI explanations that enable humans to specify the counterfactual predictions. In light of these findings, we deeply deem that, instead of designating user demands by XAI researchers during AI system development, empowering users to communicate with AI systems for their practical XAI demands is critical to unleashing useful AI explanations (RQ3). To this end, we developed an interactive XAI system via conversations that improved the usefulness of AI explanations in terms of human-perceived performance in AI-assisted writing tasks. Overall, we summarize this doctoral research by discussing the limitations and challenges of human-centered useful AI explanations.

This book presents an overview and several applications of explainable artificial intelligence (XAI). It covers different aspects related to explainable artificial intelligence, such as the need to make the AI models interpretable, how black box machine/deep learning models can be understood using various XAI methods, different evaluation metrics for XAI, human-centered explainable AI, and applications of explainable AI in health care, security surveillance, transportation, among other areas. The book is suitable for students and academics aiming to build up their background on explainable AI and can guide them in making machine/deep learning models more transparent. The book can be used as a reference book for teaching a graduate course on artificial intelligence, applied machine learning, or neural networks. Researchers working in the area of AI can use this book to discover the recent developments in XAI. Besides its use in academia, this book could be used by practitioners in AI industries, healthcare industries, medicine, autonomous vehicles, and security surveillance, who would like to develop AI techniques and applications with explanations.