Explainable Agency in Artificial Intelligence

ISBN-13: 9781032392585 / Miękka / 2024 / 192 str.

Opis

The book is a collection of cutting-edge research on the topic of explainable agency in artificial intelligence (XAI), including counterfactuals, fairness, human evaluations, and iterative and active communication among agents.

Spis treści

1. Introduction 1.1. Definition of Explainable Agency 1.2. Historical Perspective 1.3. Motivation 2. Interactivity and Explainability 2.1. Position papers by interactivity panel 3. Causality and Explainability 3.1. Position papers by causality panel 4. Counterfactual Explanations 5. Explainable Agents and Multiagent Systems 6. Fairness and Accountability in Explainable Systems 7. User-centered Approaches 8. Discussion and Future Directions

O autorze

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 Técnico. 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.