Explainable Agency in Artificial Intelligence: Research and Practice

ยท
ยท CRC Press
แƒ”แƒšแƒฌแƒ˜แƒ’แƒœแƒ˜
170
แƒ’แƒ•แƒ”แƒ แƒ“แƒ˜
แƒ›แƒ˜แƒกแƒแƒฆแƒ”แƒ‘แƒ˜

แƒแƒ› แƒ”แƒšแƒฌแƒ˜แƒ’แƒœแƒ˜แƒก แƒจแƒ”แƒกแƒแƒฎแƒ”แƒ‘

This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agentโ€™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 focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agentโ€™s reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for...

แƒแƒฆแƒ›แƒแƒแƒฉแƒ˜แƒœแƒ”แƒ— แƒ›แƒ”แƒขแƒ˜

แƒแƒ•แƒขแƒแƒ แƒ˜แƒก แƒจแƒ”แƒกแƒแƒฎแƒ”แƒ‘

Dr. Silvia Tulli is an Assistant Professor at Sorbonne University. She received her Marie Curie ITN research fellowship and completed her Ph.D. at Instituto Superior Tรฉcnico. Her research interests lie at the intersection of explainable AI, interactive machine learning, and reinforcement learning.

Dr. David W. Aha (UC Irvine, 1990) serves as the Director of the AI Center at the Naval Research Laboratory in Washington, DC. His research interests include goal reasoning agents, deliberative autonomy, case-based reasoning, explainable AI, machine learning (ML), reproducible studies, and related topics.

Dr. Silvia Tulli is an Assistant Professor at Sorbonne University. She received her Marie Curie ITN research fellowship and completed her Ph.D. at Instituto Superior Tรฉcnico. Her research interests lie at the intersection of explainable AI, interactive machine learning, and reinforcement learning...

แƒจแƒ”แƒแƒคแƒแƒกแƒ”แƒ— แƒ”แƒก แƒ”แƒšแƒฌแƒ˜แƒ’แƒœแƒ˜

แƒ’แƒ•แƒ˜แƒ—แƒฎแƒแƒ แƒ˜แƒ— แƒ—แƒฅแƒ•แƒ”แƒœแƒ˜ แƒแƒ–แƒ แƒ˜.

แƒ˜แƒœแƒคแƒแƒ แƒ›แƒแƒชแƒ˜แƒ แƒฌแƒแƒ™แƒ˜แƒ—แƒฎแƒ•แƒแƒกแƒ—แƒแƒœ แƒ“แƒแƒ™แƒแƒ•แƒจแƒ˜แƒ แƒ”แƒ‘แƒ˜แƒ—

แƒกแƒ›แƒแƒ แƒขแƒคแƒแƒœแƒ”แƒ‘แƒ˜ แƒ“แƒ แƒขแƒแƒ‘แƒšแƒ”แƒขแƒ”แƒ‘แƒ˜
แƒ“แƒแƒแƒ˜แƒœแƒกแƒขแƒแƒšแƒ˜แƒ แƒ”แƒ— Google Play Books แƒแƒžแƒ˜ Android แƒ“แƒ iPad/iPhone แƒ›แƒแƒฌแƒงแƒแƒ‘แƒ˜แƒšแƒแƒ‘แƒ”แƒ‘แƒ˜แƒกแƒ—แƒ•แƒ˜แƒก. แƒ˜แƒก แƒแƒ•แƒขแƒแƒ›แƒแƒขแƒฃแƒ แƒแƒ“ แƒ’แƒแƒœแƒแƒฎแƒแƒ แƒชแƒ˜แƒ”แƒšแƒ”แƒ‘แƒก แƒกแƒ˜แƒœแƒฅแƒ แƒแƒœแƒ˜แƒ–แƒแƒชแƒ˜แƒแƒก แƒ—แƒฅแƒ•แƒ”แƒœแƒก แƒแƒœแƒ’แƒแƒ แƒ˜แƒจแƒ—แƒแƒœ แƒ“แƒ แƒกแƒแƒจแƒฃแƒแƒšแƒ”แƒ‘แƒแƒก แƒ›แƒแƒ’แƒชแƒ”แƒ›แƒ—, แƒฌแƒแƒ˜แƒ™แƒ˜แƒ—แƒฎแƒแƒ— แƒกแƒแƒกแƒฃแƒ แƒ•แƒ”แƒšแƒ˜ แƒ™แƒแƒœแƒขแƒ”แƒœแƒขแƒ˜ แƒœแƒ”แƒ‘แƒ˜แƒกแƒ›แƒ˜แƒ”แƒ  แƒแƒ“แƒ’แƒ˜แƒšแƒแƒก, แƒ แƒแƒ’แƒแƒ แƒช แƒแƒœแƒšแƒแƒ˜แƒœ, แƒ˜แƒกแƒ” แƒฎแƒแƒ–แƒ’แƒแƒ แƒ”แƒจแƒ” แƒ แƒ”แƒŸแƒ˜แƒ›แƒจแƒ˜.
แƒšแƒ”แƒžแƒขแƒแƒžแƒ”แƒ‘แƒ˜ แƒ“แƒ แƒ™แƒแƒ›แƒžแƒ˜แƒฃแƒขแƒ”แƒ แƒ”แƒ‘แƒ˜
Google Play-แƒจแƒ˜ แƒจแƒ”แƒซแƒ”แƒœแƒ˜แƒšแƒ˜ แƒแƒฃแƒ“แƒ˜แƒแƒฌแƒ˜แƒ’แƒœแƒ”แƒ‘แƒ˜แƒก แƒ›แƒแƒกแƒ›แƒ”แƒœแƒ แƒ—แƒฅแƒ•แƒ”แƒœแƒ˜ แƒ™แƒแƒ›แƒžแƒ˜แƒฃแƒขแƒ”แƒ แƒ˜แƒก แƒ•แƒ”แƒ‘-แƒ‘แƒ แƒแƒฃแƒ–แƒ”แƒ แƒ˜แƒก แƒ’แƒแƒ›แƒแƒงแƒ”แƒœแƒ”แƒ‘แƒ˜แƒ— แƒจแƒ”แƒ’แƒ˜แƒซแƒšแƒ˜แƒแƒ—.
แƒ”แƒšแƒฌแƒแƒ›แƒ™แƒ˜แƒ—แƒฎแƒ•แƒ”แƒšแƒ”แƒ‘แƒ˜ แƒ“แƒ แƒกแƒฎแƒ•แƒ แƒ›แƒแƒฌแƒงแƒแƒ‘แƒ˜แƒšแƒแƒ‘แƒ”แƒ‘แƒ˜
แƒ”แƒšแƒ”แƒฅแƒขแƒ แƒแƒœแƒฃแƒšแƒ˜ แƒ›แƒ”แƒšแƒœแƒ˜แƒก แƒ›แƒแƒฌแƒงแƒแƒ‘แƒ˜แƒšแƒแƒ‘แƒ”แƒ‘แƒ–แƒ” แƒฌแƒแƒกแƒแƒ™แƒ˜แƒ—แƒฎแƒแƒ“, แƒ แƒแƒ’แƒแƒ แƒ˜แƒชแƒแƒ Kobo eReaders, แƒ—แƒฅแƒ•แƒ”แƒœ แƒฃแƒœแƒ“แƒ แƒฉแƒแƒ›แƒแƒขแƒ•แƒ˜แƒ แƒ—แƒแƒ— แƒคแƒแƒ˜แƒšแƒ˜ แƒ“แƒ แƒ’แƒแƒ“แƒแƒ˜แƒขแƒแƒœแƒแƒ— แƒ˜แƒ’แƒ˜ แƒ—แƒฅแƒ•แƒ”แƒœแƒก แƒ›แƒแƒฌแƒงแƒแƒ‘แƒ˜แƒšแƒแƒ‘แƒแƒจแƒ˜. แƒ“แƒแƒฎแƒ›แƒแƒ แƒ”แƒ‘แƒ˜แƒก แƒชแƒ”แƒœแƒขแƒ แƒ˜แƒก แƒ“แƒ”แƒขแƒแƒšแƒฃแƒ แƒ˜ แƒ˜แƒœแƒกแƒขแƒ แƒฃแƒฅแƒชแƒ˜แƒ”แƒ‘แƒ˜แƒก แƒ›แƒ˜แƒฎแƒ”แƒ“แƒ•แƒ˜แƒ— แƒ’แƒแƒ“แƒแƒ˜แƒขแƒแƒœแƒ”แƒ— แƒคแƒแƒ˜แƒšแƒ”แƒ‘แƒ˜ แƒ›แƒฎแƒแƒ แƒ“แƒแƒญแƒ”แƒ แƒ˜แƒš แƒ”แƒšแƒฌแƒแƒ›แƒ™แƒ˜แƒ—แƒฎแƒ•แƒ”แƒšแƒ”แƒ‘แƒ–แƒ”.