Robust Explainable AI
Buch in deiner Nähe kaufen
Beschreibung
The area of Explainable Artificial Intelligence (XAI) is concerned with providing methods and tools to improve the interpretability of black-box learning models. While several approaches exist to generate explanations, they are often lacking robustness, e.g., they may produce completely different explanations for similar events. This phenomenon has troubling implications, as lack of robustness indicates that explanations are not capturing the underlying decision-making process of a model and thus cannot be trusted.
This book aims at introducing Robust Explainable AI, a rapidly growing field whose focus is to ensure that explanations for machine learning models adhere to the highest robustness standards. We will introduce the most important concepts, methodologies, and results in the field, with a particular focus on techniques developed for feature attribution methods and counterfactual explanations for deep neural networks.
As prerequisites, a certain familiarity with neural networks and approaches within XAI is desirable but not mandatory. The book is designed to be self-contained, and relevant concepts will be introduced when needed, together with examples to ensure a successful learning experience.
The book is the first to introduce Robust Explainable AI, a rapidly growing field Is designed to be self-contained, a familiarity with neural networks or XAI being desirable but not mandatory Presents the most important methods on feature attribution and counterfactual explanations for deep neural networks
Autor*in
Francesco Leofante
Themen in »Robust Explainable AI«
Adversarial Robustness Counterfactual Explanations Deep Neural Networks Explainable AI Fairness Feature Attribution Saliency-Based Explanations Trustworthy AI XAI