Explainable Fuzzy Systems

The importance of Trustworthy and Explainable Artificial Intelligence (XAI) is recognized in academia, industry and society. This book introduces tools for dealing with imprecision and uncertainty in XAI applications where explanations are demanded, mainly in natural language. Design of Explainable Fuzzy Systems (EXFS) is rooted in Interpretable Fuzzy Systems, which are thoroughly covered in the book. The idea of interpretability in fuzzy systems, which is grounded on mathematical constraints and assessment functions, is firstly introduced. Then, design methodologies are described. Finally, the book shows with practical examples how to design EXFS from interpretable fuzzy systems and natural language generation. This approach is supported by open source software. The book is intended for researchers, students and practitioners who wish to explore EXFS from theoretical and practical viewpoints. The breadth of coverage will inspire novel applications and scientific advancements.

This book focuses on an overview of the AI techniques, their foundations, their applications, and remaining challenges and open problems. Many artificial intelligence (AI) techniques do not explain their recommendations. Providing natural-language explanations for numerical AI recommendations is one of the main challenges of modern AI. To provide such explanations, a natural idea is to use techniques specifically designed to relate numerical recommendations and natural-language descriptions, namely fuzzy techniques. This book is of interest to practitioners who want to use fuzzy techniques to make AI applications explainable, to researchers who may want to extend the ideas from these papers to new application areas, and to graduate students who are interested in the state-of-the-art of fuzzy techniques and of explainable AI—in short, to anyone who is interested in problems involving fuzziness and AI in general.

Modern AI techniques –- especially deep learning –- provide, in many cases, very good recommendations: where a self-driving car should go, whether to give a company a loan, etc. The problem is that not all these recommendations are good -- and since deep learning provides no explanations, we cannot tell which recommendations are good. It is therefore desirable to provide natural-language explanation of the numerical AI recommendations. The need to connect natural language rules and numerical decisions is known since 1960s, when the need emerged to incorporate expert knowledge -- described by imprecise words like "small" -- into control and decision making. For this incorporation, a special "fuzzy" technique was invented, that led to many successful applications. This book described how this technique can help to make AI more explainable.The book can be recommended for students, researchers, and practitioners interested in explainable AI.

The third edition of this textbook presents a further updated approach to fuzzy sets and systems that can model uncertainty — i.e., “type-2” fuzzy sets and systems. The author demonstrates how to overcome the limitations of classical fuzzy sets and systems, enabling a wide range of applications, from time-series forecasting to knowledge mining to classification to control and to explainable AI (XAI). This latest edition again begins by introducing classical (type-1) fuzzy sets and systems, and then explains how they can be modified to handle uncertainty, leading to type-2 fuzzy sets and systems. New material is included about how to obtain fuzzy set word models that are needed for XAI, similarity of fuzzy sets, a quantitative methodology that lets one explain in a simple way why the different kinds of fuzzy systems have the potential for performance improvements over each other, and new parameterizations of membership functions that have the potential for achieving even greater performance for all kinds of fuzzy systems. For hands-on experience, the book provides information on accessing MATLAB, Java, and Python software to complement the content. The book features a full suite of classroom material.

The book proposes techniques, with an emphasis on the financial sector, which will make recommendation systems both accurate and explainable. The vast majority of AI models work like black box models. However, in many applications, e.g., medical diagnosis or venture capital investment recommendations, it is essential to explain the rationale behind AI systems decisions or recommendations. Therefore, the development of artificial intelligence cannot ignore the need for interpretable, transparent, and explainable models. First, the main idea of the explainable recommenders is outlined within the background of neuro-fuzzy systems. In turn, various novel recommenders are proposed, each characterized by achieving high accuracy with a reasonable number of interpretable fuzzy rules. The main part of the book is devoted to a very challenging problem of stock market recommendations. An original concept of the explainable recommender, based on patterns from previous transactions, is developed; it recommends stocks that fit the strategy of investors, and its recommendations are explainable for investment advisers.

The second edition of this textbook provides a fully updated approach to fuzzy sets and systems that can model uncertainty — i.e., “type-2” fuzzy sets and systems. The author demonstrates how to overcome the limitations of classical fuzzy sets and systems, enabling a wide range of applications from time-series forecasting to knowledge mining to control. In this new edition, a bottom-up approach is presented that begins by introducing classical (type-1) fuzzy sets and systems, and then explains how they can be modified to handle uncertainty. The author covers fuzzy rule-based systems – from type-1 to interval type-2 to general type-2 – in one volume. For hands-on experience, the book provides information on accessing MatLab and Java software to complement the content. The book features a full suite of classroom material.

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.

In the early 1970s, fuzzy systems and fuzzy control theories added a new dimension to control systems engineering. From its beginnings as mostly heuristic and somewhat ad hoc, more recent and rigorous approaches to fuzzy control theory have helped make it an integral part of modern control theory and produced many exciting results. Yesterday's "art