eXplainable AI: Interpreting Machine Learning with XAI

In recent years, artificial intelligence (AI) has made remarkable progress, allowing machines to perform a variety of tasks that were previously thought to be only humanly possible. However, as AI systems' complexity has grown, so have concerns about their trustworthiness, fairness, and accountability, particularly in high-stakes domains such as healthcare, finance, and banking systems. To address these issues, the field of Explainable Artificial Intelligence (XAI) has emerged, with the goal of developing AI systems capable of providing understandable and interpretable explanations for their decisions and behaviors.

In this book, we present a hands-on guide to XAI techniques using KNIME, where we provide a step-by-step introduction to the key concepts and tools, accompanied by real-world examples and case studies. Our goal is to enable readers, regardless of background, to understand and apply XAI techniques in their own projects. We demonstrate how popular XAI techniques such as LIME, SHAP, etc. can be implemented in KNIME using various nodes and components.