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 provides a first course on deep learning in computational mechanics. The book starts with a short introduction to machine learning's fundamental concepts before neural networks are explained thoroughly. It then provides an overview of current topics in physics and engineering, setting the stage for the book's main topics: physics-informed neural networks and the deep energy method. The idea of the book is to provide the basic concepts in a mathematically sound manner and yet to stay as simple as possible. To achieve this goal, mostly one-dimensional examples are investigated, such as approximating functions by neural networks or the simulation of the temperature's evolution in a one-dimensional bar. Each chapter contains examples and exercises which are either solved analytically or in PyTorch, an open-source machine learning framework for python.

Processing information and analyzing data efficiently and effectively is crucial for any company that wishes to stay competitive in its respective market. Nonlinear data presents new challenges to organizations, however, due to its complexity and unpredictability. The only technology that can properly handle this form of data is artificial neural networks. These modeling systems present a high level of benefits in analyzing complex data in a proficient manner, yet considerable research on the specific applications of these intelligent components is significantly deficient. Applications of Artificial Neural Networks for Nonlinear Data is a collection of innovative research on the contemporary nature of artificial neural networks and their specific implementations within data analysis. While highlighting topics including propagation functions, optimization techniques, and learning methodologies, this book is ideally designed for researchers, statisticians, academicians, developers, scientists, practitioners, students, and educators seeking current research on the use of artificial neural networks in diagnosing and solving nonparametric problems.

The research presented in this book shows how combining deep neural networks with a special class of fuzzy logical rules and multi-criteria decision tools can make deep neural networks more interpretable - and even, in many cases, more efficient. Fuzzy logic together with multi-criteria decision-making tools provides very powerful tools for modeling human thinking. Based on their common theoretical basis, we propose a consistent framework for modeling human thinking by using the tools of all three fields: fuzzy logic, multi-criteria decision-making, and deep learning to help reduce the black-box nature of neural models; a challenge that is of vital importance to the whole research community.

In recent years, Higher Order Neural Networks (HONNs) have been widely adopted by researchers for applications in control signal generating, pattern recognition, nonlinear recognition, classification, and predition of control and recognition scenarios. Due to the fact that HONNs have been proven to be faster, more accurate, and easier to explain than traditional neural networks, their applications are limitless. Applied Artificial Higher Order Neural Networks for Control and Recognition explores the ways in which higher order neural networks are being integrated specifically for intelligent technology applications. Emphasizing emerging research, practice, and real-world implementation, this timely reference publication is an essential reference source for researchers, IT professionals, and graduate-level computer science and engineering students.

With artificial neural network research being one of the new directions for new generation computers, current research suggests that open-box artificial higher order neural networks (HONNs) play an important role in this new direction.Artificial Higher Order Neural Networks for Modeling and Simulation introduces artificial Higher Order Neural Networks (HONNs) to professionals working in the fields of modeling and simulation, and explains that HONN is an open-box artificial neural network tool as compared to traditional artificial neural networks. Including details of the most popular HONN models, this book provides an opportunity for practitioners in the field of modeling and simulations to understand and know how to use HONNS in their area of expertise.

This book describes new theories and applications of artificial neural networks, with a special focus on answering questions in neuroscience, biology and biophysics and cognitive research. It covers a wide range of methods and technologies, including deep neural networks, large scale neural models, brain computer interface, signal processing methods, as well as models of perception, studies on emotion recognition, self-organization and many more. The book includes both selected and invited papers presented at the XXII International Conference on Neuroinformatics, held on October 12-16, 2020, Moscow, Russia.

This book bridges the communication gap between neuroscientists and engineers through the unifying theme of correlation-based learning

Developing brain-style signal processing or machine learning algorithms has attracted many sharp minds from a range of disciplines. Now, coauthored by four researchers with varying backgrounds in signal processing, neuroscience, psychology, and computer science, Correlative Learning unifies the many cross-fertilized ideas in computational neuroscience and signal processing in a common language that will help engineers understand and appreciate the human brain as a highly sophisticated biosystem for building more intelligent machines.

First, the authors present the necessary neuroscience background for engineers, and then go on to relate the common intrinsic structures of the learning mechanisms of the brain to signal processing, machine learning, kernel learning, complex-valued domains, and the ALOPEX learning paradigm.

This correlation-based approach to building complex, reliable (robust), and adaptive systems is vital for engineers, researchers, and graduate students from various fields of science and engineering. Figures, tables, worked examples, and case studies illustrate how to use computational tools for either helping to understand brain functions or fitting specific engineering applications, and a comprehensive bibliography covering over 1,000 references from major publications is included for further reading.

Forecasting is one of the most important activities that form the basis for strategic, tactical, and operational decisions in all business organizations. Recently, neural networks have emerged as an important tool for business forecasting. There are considerable interests and applications in forecasting using neural networks. Neural Networks in Business Forecasting provides for researchers and practitioners some recent advances in applying neural networks to business forecasting. A number of case studies demonstrating the innovative or successful applications of neural networks to many areas of business as well as methods to improve neural network forecasting performance are presented.

The unification of symbolist and connectionist models is a major trend in AI. The key is to keep the symbolic semantics unchanged. Unfortunately, present embedding approaches cannot. The approach in this book makes the unification possible. It is indeed a new and promising approach in AI. -Bo Zhang, Director of AI Institute, Tsinghua It is indeed wonderful to see the reviving of the important theme Nural Symbolic Model. Given the popularity and prevalence of deep learning, symbolic processing is often neglected or downplayed. This book confronts this old issue head on, with a historical look, incorporating recent advances and new perspectives, thus leading to promising new methods and approaches. -Ron Sun (RPI), on Governing Board of Cognitive Science Society Both for language and humor, approaches like those described in this book are the way to snickerdoodle wombats. -Christian F. Hempelmann (Texas A&M-Commerce) on Executive Board of International Society for Humor Studies

This book summarizes years of research in the field of fuzzy relational programming, with a special emphasis on geometric models. It discusses the state-of-the-art in fuzzy relational geometric problems, together with key open issues that must be resolved to achieve a more efficient application of this method. Though chiefly based on research conducted by the authors, who were the first to introduce fuzzy geometric problems, it also covers important findings obtained in the field of linear and non-linear programming. Thanks to its balance of basic and advanced concepts, and its wealth of practical examples, the book offers a valuable guide for both newcomers and experienced researcher in the fields of soft computing and mathematical optimization.

A comprehensive introduction to network flows that brings together the classic and the contemporary aspects of the field, and provides an integrative view of theory, algorithms, and applications.

In the fast pace of the modern world it is important, more than ever, for factories to know how and why their machines are failing and what can be done to prevent it. As such, it is imperative that new research is conducted to make sure that factories can operate as efficiently as possible. Fuzzy Logic Dynamics and Machine Prediction for Failure Analysis is an essential reference source for the newest research on the risk assessment matrix, ladder logic, and computerized maintenance management systems (CMMS). Featuring widespread coverage across a variety of related viewpoints and topics, such as the Ishikawa diagram, machinery failure analysis and troubleshooting, model reference adaptive control systems, and proportional-integral-derivative (PID) controllers, this book is ideally designed for professionals, upper-level students, and academics seeking current research on the implementation of fuzzy logic in machine prediction failure.

In the design of a neural network, either for biological modeling, cognitive simulation, numerical computation or engineering applications, it is important to investigate the network's computational performance which is usually described by the long-term behaviors, called dynamics, of the model equations. The purpose of this book is to give an introduction to the mathematical modeling and analysis of networks of neurons from the viewpoint of dynamical systems.

Now, for the first time, publication of the landmark work in backpropagation Scientists, engineers, statisticians, operations researchers, and other investigators involved in neural networks have long sought direct access to Paul Werbos's groundbreaking, much-cited 1974 Harvard doctoral thesis, The Roots of Backpropagation, which laid the foundation of backpropagation. Now, with the publication of its full text, these practitioners can go straight to the original material and gain a deeper, practical understanding of this unique mathematical approach to social studies and related fields. In addition, Werbos has provided three more recent research papers, which were inspired by his original work, and a new guide to the field. Originally written for readers who lacked any knowledge of neural nets, The Roots of Backpropagation firmly established both its historical and continuing significance as it:
* Demonstrates the ongoing value and new potential of backpropagation
* Creates a wealth of sound mathematical tools useful across disciplines
* Sets the stage for the emerging area of fast automatic differentiation
* Describes new designs for forecasting and control which exploit backpropagation
* Unifies concepts from Freud, Jung, biologists, and others into a new mathematical picture of the human mind and how it works
* Certifies the viability of Deutsch's model of nationalism as a predictive tool--as well as the utility of extensions of this central paradigm
"What a delight it was to see Paul Werbos rediscover Freud's version of 'back-propagation.' Freud was adamant (in The Project for a Scientific Psychology) that selective learning could only take place if the presynaptic neuron was as influenced as is the postsynaptic neuron during excitation. Such activation of both sides of the contact barrier (Freud's name for the synapse) was accomplished by reducing synaptic resistance by the absorption of 'energy' at the synaptic membranes. Not bad for 1895 But Werbos 1993 is even better." --Karl H. Pribram Professor Emeritus, Stanford University

Robust and Fault-Tolerant Control proposes novel automatic control strategies for nonlinear systems developed by means of artificial neural networks and pays special attention to robust and fault-tolerant approaches. The book discusses robustness and fault tolerance in the context of model predictive control, fault accommodation and reconfiguration, and iterative learning control strategies. Expanding on its theoretical deliberations the monograph includes many case studies demonstrating how the proposed approaches work in practice. The most important features of the book include: a comprehensive review of neural network architectures with possible applications in system modelling and control; a concise introduction to robust and fault-tolerant control; step-by-step presentation of the control approaches proposed; an abundance of case studies illustrating the important steps in designing robust and fault-tolerant control; and a large number of figures and tables facilitating the performance analysis of the control approaches described. The material presented in this book will be useful for researchers and engineers who wish to avoid spending excessive time in searching neural-network-based control solutions. It is written for electrical, computer science and automatic control engineers interested in control theory and their applications. This monograph will also interest postgraduate students engaged in self-study of nonlinear robust and fault-tolerant control.

Two of the most important factors contributing to national and international economy are processing of information for accurate financial forecasting and decision making as well as processing of information for efficient control of manufacturing systems for increased productivity. The associated problems are very complex and conventional methods often fail to produce acceptable solutions. Moreover, businesses and industries always look for superior solutions to boost profitability and productivity. In recent times, artificial neural networks have demonstrated promising results in solving many real-world problems in these domains, and these techniques are increasingly gaining business and industry acceptance among the practitioners. ""Artificial Neural Networks in Finance and Manufacturing"" presents many state-of-the-art and diverse applications to finance and manufacturing, along with underlying neural network theories and architectures. It offers researchers and practitioners the opportunity to access exciting and cutting-edge research focusing on neural network applications, combining two aspects of economic domain in a single and consolidated volume.

This book presents a comprehensive discussion on the characterization of vagueness in pictures. It reports on how the problem of representation of images has been approached in scientific practice, highlighting the role of mathematical methods and the philosophical background relevant for issues such as representation, categorization and reasoning. Without delving too much into the technical details, the book examines and defends different kinds of values of fuzziness based on a complex approach to categorization as a practice, adopting conceptual and empirical suggestions from different fields including the arts. It subsequently advances criticisms and provides suggestions for interpretation and application. By describing a cognitive framework based on fuzzy, rough and near sets, and discussing all of the relevant mathematical and philosophical theories for the representation and processing of vagueness in images, the book offers a practice-oriented guide to fuzzy visual reasoning, along with novel insights into the field of interpreting and thinking with fuzzy pictures and fuzzy data.

This book offers a multifaceted perspective on fuzzy set theory, discussing its developments over the last 50 years. It reports on all types of fuzzy sets, from ordinary to hesitant fuzzy sets, with each one explained by its own developers, authoritative scientists well known for their previous works. Highlighting recent theorems and proofs, the book also explores how fuzzy set theory has come to be extensively used in almost all branches of science, including the health sciences, decision science, earth science and the social sciences alike. It presents a wealth of real-world sample applications, from routing problem to robotics, and from agriculture to engineering. By offering a comprehensive, timely and detailed portrait of the field, the book represents an excellent reference guide for researchers, lecturers and postgraduate students pursuing research on new fuzzy set extensions.

As the increased demand for high-speed communication creates an interest in the development of optical networks, intelligent all optical networks have emerged as the next generation for reliable and fast connections. Intelligent Systems for Optical Networks Design: Advancing Techniques is a comprehensive collection of research focused on theoretical and practical aspects of intelligent methodologies as applied to real world problems. This reference source is useful for research and development engineers, scholars, and students interested in the latest development in the area of intelligent systems for optical networks design.

This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling.

This book shows that the term "interpretability" goes far beyond the concept of readability of a fuzzy set and fuzzy rules. It focuses on novel and precise operators of aggregation, inference, and defuzzification leading to flexible Mamdani-type and logical-type systems that can achieve the required accuracy using a less complex rule base. The individual chapters describe various aspects of interpretability, including appropriate selection of the structure of a fuzzy system, focusing on improving the interpretability of fuzzy systems designed using both gradient-learning and evolutionary algorithms. It also demonstrates how to eliminate various system components, such as inputs, rules and fuzzy sets, whose reduction does not adversely affect system accuracy. It illustrates the performance of the developed algorithms and methods with commonly used benchmarks. The book provides valuable tools for possible applications in many fields including expert systems, automatic control and robotics.