Explainable, Interpretable, and Transparent AI Systems

Transparent Artificial Intelligence (AI) systems facilitate understanding of the decision-making process and provide opportunities in various aspects of explaining AI models. This book provides up-to-date information on the latest advancements in the field of explainable AI, which is a critical requirement of AI, Machine Learning (ML), and Deep Learning (DL) models. It provides examples, case studies, latest techniques, and applications from domains such as healthcare, finance, and network security. It also covers open-source interpretable tool kits so that practitioners can use them in their domains.

Features:

• Presents a clear focus on the application of explainable AI systems while tackling important issues of “interpretability” and “transparency”.
• Reviews adept handling with respect to existing software and evaluation issues of interpretability.
• Provides insights into simple interpretable models such as decision trees, decision rules, and linear regression.
• Focuses on interpreting black box models like feature importance and accumulated local effects.
• Discusses capabilities of explainability and interpretability.

This book is aimed at graduate students and professionals in computer engineering and networking communications.