This is an open access book.Statistical machine learning (ML) has triggered a renaissance of artificial intelligence (AI). While the most successful ML models, including Deep Neural Networks (DNN), have developed better predictivity, they have become increasingly complex, at the expense of human interpretability (correlation vs. causality). The field of explainable AI (xAI) has emerged with the goal of creating tools and models that are both predictive and interpretable and understandable for humans. Explainable AI is receiving huge interest in the machine learning and AI research communities, across academia, industry, and government, and there is now an excellent opportunity to push towards successful explainable AI applications. This volume will help the research community to accelerate this process, to promote a more systematic use of explainable AI to improve models in diverse applications, and ultimately to better understand how current explainable AI methods need to be improved and what kind of theory of explainable AI is needed. After overviews of current methods and challenges, the editors include chapters that describe new developments in explainable AI. The contributions are from leading researchers in the field, drawn from both academia and industry, and many of the chapters take a clear interdisciplinary approach to problem-solving. The concepts discussed include explainability, causability, and AI interfaces with humans, and the applications include image processing, natural language, law, fairness, and climate science.

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.