There is a growing global interest in harnessing diverse AI techniques and tools to power the next wave of business and IT applications. AI capabilities are being integrated into resource-intensive devices, machines, and equipment across various settings, enabling connected products to operate intelligently—either individually or as part of a network.
AI is widely regarded as the transformative technology for building intelligent systems, networks, and environments. However, the widespread adoption of AI brings challenges, particularly around understanding how AI models make decisions. Trust and transparency have become major concerns. One promising approach to address these issues is the use of knowledge graphs, which can be linked to AI systems to enhance explainability and support the goals of explainable AI (XAI).
This book delves into the concepts, tools, frameworks, and techniques of explainable AI. The authors highlight the role of knowledge graphs in making AI systems more transparent and trustworthy. They also demonstrate how these technologies can be applied to explain data fabric solutions and improve the effectiveness of intelligent applications in sectors like finance and healthcare.
Explainable Artificial Intelligence (XAI): Concepts, Enabling Tools, Technologies and Applications is intended for industry and academic researchers, scientists, engineers, lecturers, and advanced students in IT, computer science, soft computing, AI/ML/DL, data science, the semantic web, knowledge engineering, and IoT. It is also a valuable resource for software, product, and project managers and developers working in these areas.
