Explainable Agency In Artificial Intelligence

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies. The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems. Features: Contributes to the topic of explainable artificial intelligence (XAI) Focuses on the XAI subtopic of explainable agency Includes an introductory chapter, a survey, and five other original contributions

This book constitutes the proceedings of the First International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems, EXTRAAMAS 2019, held in Montreal, Canada, in May 2019. The 12 revised and extended papers presented were carefully selected from 23 submissions. They are organized in topical sections on explanation and transparency; explainable robots; opening the black box; explainable agent simulations; planning and argumentation; explainable AI and cognitive science.

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent’s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies. The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems. Features: • Contributes to the topic of explainable artificial intelligence (XAI) • Focuses on the XAI subtopic of explainable agency • Includes an introductory chapter, a survey, and five other original contributions

This book constitutes the proceedings of the Second International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems, EXTRAAMAS 2020, which was due to be held in Auckland, New Zealand, in May 2020. The conference was held virtually due to the COVID-19 pandemic. The 8 revised and extended papers were carefully selected from 20 submissions and are presented here with one demo paper. The papers are organized in the following topical sections: explainable agents; cross disciplinary XAI; explainable machine learning; demos.

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 development of “intelligent” systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to “intelligent” machines. For sensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner. The 22 chapters included in this book provide a timely snapshot of algorithms, theory, and applications of interpretable and explainable AI and AI techniques that have been proposed recently reflecting the current discourse in this field and providing directions of future development. The book is organized in six parts: towards AI transparency; methods for interpreting AI systems; explaining the decisions of AI systems; evaluating interpretability and explanations; applications of explainable AI; and software for explainable AI.

From simple cases such as hook and latch attachments found in Velcro to articulated-wing flying vehicles, biology often has been used to inspire many creative design ideas. The scientific challenge now is to transform the paradigm into a repeatable and scalable methodology. Biologically Inspired Design explores computational techniques and tools that can help integrate the method into design practice. With an inspiring foreword from Janine Benyus, Biologically Inspired Design contains a dozen chapters written by some of the leading scholars in the transdisciplinary field of bioinspired design, such as Frank Fish, Julian Vincent and Jeannette Yen from biology, and Amaresk Chakrabarti, Satyandra Gupta and Li Shu from engineering. Based in part on discussions at two workshops sponsored by the United States National Science Foundation, this volume introduces and develops several methods and tools for bioinspired design including: Information-processing theories, Natural language techniques, Knowledge-based tools, and Functional approaches and Pedagogical techniques. By exploring these fundamental theories, techniques and tools for supporting biologically inspired design, this volume provides a comprehensive resource for design practitioners wishing to explore the paradigm, an invaluable guide to design educators interested in teaching the method, and a preliminary reading for design researchers wanting to investigate bioinspired design.

This three-volume set constitutes the refereed proceedings of the First World Conference on Explainable Artificial Intelligence, xAI 2023, held in Lisbon, Portugal, in July 2023. The 94 papers presented were thoroughly reviewed and selected from the 220 qualified submissions. They are organized in the following topical sections: ​ Part I: Interdisciplinary perspectives, approaches and strategies for xAI; Model-agnostic explanations, methods and techniques for xAI, Causality and Explainable AI; Explainable AI in Finance, cybersecurity, health-care and biomedicine. Part II: Surveys, benchmarks, visual representations and applications for xAI; xAI for decision-making and human-AI collaboration, for Machine Learning on Graphs with Ontologies and Graph Neural Networks; Actionable eXplainable AI, Semantics and explainability, and Explanations for Advice-Giving Systems. Part III: xAI for time series and Natural Language Processing; Human-centered explanations and xAI for Trustworthy and Responsible AI; Explainable and Interpretable AI with Argumentation, Representational Learning and concept extraction for xAI.