You may have to Search all our reviewed books and magazines, click the sign up button below to create a free account.
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.
Delving into the deeply enigmatic nature of Artificial Intelligence (AI), AI: Unexplainable, Unpredictable, Uncontrollable explores the various reasons why the field is so challenging. Written by one of the founders of the field of AI safety, this book addresses some of the most fascinating questions facing humanity, including the nature of intelligence, consciousness, values and knowledge. Moving from a broad introduction to the core problems, such as the unpredictability of AI outcomes or the difficulty in explaining AI decisions, this book arrives at more complex questions of ownership and control, conducting an in-depth analysis of potential hazards and unintentional consequences. The bo...
Imagine a world where the boundaries of creativity are not only stretched but redefined. This book serves as your guide to this new frontier, engaging general readers, tech enthusiasts, and creatives alike in the captivating interplay between human ingenuity and artificial intelligence (AI). Journey through the ground-breaking advancements in AI as they intersect with art, design, entertainment, and education. Discover how AI’s power to analyze and understand language can be harnessed to generate breathtaking visuals from mere text descriptions—a process known as text-conditional image generation. But this book goes beyond just showcasing AI’s capabilities: it delves into its transform...
An Introduction to Universal Artificial Intelligence provides the formal underpinning of what it means for an agent to act intelligently in an unknown environment. First presented in Universal Algorithmic Intelligence (Hutter, 2000), UAI offers a framework in which virtually all AI problems can be formulated, and a theory of how to solve them. UAI unifies ideas from sequential decision theory, Bayesian inference, and algorithmic information theory to construct AIXI, an optimal reinforcement learning agent that learns to act optimally in unknown environments. AIXI is the theoretical gold standard for intelligent behavior. The book covers both the theoretical and practical aspects of UAI. Baye...
Artificial intelligence (AI) permeates our lives in a growing number of ways. Relying solely on traditional, technology-driven approaches won't suffice to develop and deploy that technology in a way that truly enhances human experience. A new concept is desperately needed to reach that goal. That concept is Human-Centered AI (HCAI). With 29 captivating chapters, this book delves deep into the realm of HCAI. In Section I, it demystifies HCAI, exploring cutting-edge trends and approaches in its study, including the moral landscape of Large Language Models. Section II looks at how HCAI is viewed in different institutions—like the justice system, health system, and higher education—and how i...
Developing robots to interact with humans is a complex interdisciplinary effort. While engineering and social science perspectives on designing human–robot interactions (HRI) are readily available, the body of knowledge and practices related to design, specifically interaction design, often remain tacit. Designing Interactions with Robots fills an important resource gap in the HRI community, and acts as a guide to navigating design-specific methods, tools, and techniques. With contributions from the field's leading experts and rising pioneers, this collection presents state of the art knowledge and a range of design methods, tools, and techniques, which cover the various phases of an HRI project. This book is accessible to an interdisciplinary audience, and does not assume any design knowledge. It provides actionable resources whose efficacy have been tested and proven in existing research. This manual is essential for HRI design students, researchers, and practitioners alike. It offers crucial guidance for the processes involved in robot and HRI design, marking a significant stride toward advancing the HRI landscape.
This book constitutes the proceedings of the Third International Workshop on Explainable, Transparent AI and Multi-Agent Systems, EXTRAAMAS 2021, which was held virtually due to the COVID-19 pandemic. The 19 long revised papers and 1 short contribution were carefully selected from 32 submissions. The papers are organized in the following topical sections: XAI & machine learning; XAI vision, understanding, deployment and evaluation; XAI applications; XAI logic and argumentation; decentralized and heterogeneous XAI.
Robots are increasingly becoming prevalent in our daily lives within our living or working spaces. We hope that robots will take up tedious, mundane or dirty chores and make our lives more comfortable, easy and enjoyable by providing companionship and care. However, robots may pose a threat to human privacy, safety and autonomy; therefore, it is necessary to have constant control over the developing technology to ensure the benevolent intentions and safety of autonomous systems. Building trust in (autonomous) robotic systems is thus necessary. The title of this book highlights this challenge: “Trust in robots—Trusting robots”. Herein, various notions and research areas associated with robots are unified. The theme “Trust in robots” addresses the development of technology that is trustworthy for users; “Trusting robots” focuses on building a trusting relationship with robots, furthering previous research. These themes and topics are at the core of the PhD program “Trust Robots” at TU Wien, Austria.
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 ...