IEEE Press Series on Computational Intelligence

Reinforcement learning (RL) and adaptive dynamic programming (ADP) has been one of the most critical research fields in science and engineering for modern complex systems. This book describes the latest RL and ADP techniques for decision and control in human engineered systems, covering both single player decision and control and multi-player games. Edited by the pioneers of RL and ADP research, the book brings together ideas and methods from many fields and provides an important and timely guidance on controlling a wide variety of systems, such as robots, industrial processes, and economic decision-making.

Presents the latest advances in complex-valued neural networks by demonstrating the theory in a wide range of applications Complex-valued neural networks is a rapidly developing neural network framework that utilizes complex arithmetic, exhibiting specific characteristics in its learning, self-organizing, and processing dynamics. They are highly suitable for processing complex amplitude, composed of amplitude and phase, which is one of the core concepts in physical systems to deal with electromagnetic, light, sonic/ultrasonic waves as well as quantum waves, namely, electron and superconducting waves. This fact is a critical advantage in practical applications in diverse fields of engineering, where signals are routinely analyzed and processed in time/space, frequency, and phase domains. Complex-Valued Neural Networks: Advances and Applications covers cutting-edge topics and applications surrounding this timely subject. Demonstrating advanced theories with a wide range of applications, including communication systems, image processing systems, and brain-computer interfaces, this text offers comprehensive coverage of: • Conventional complex-valued neural networks • Quaternionic neural networks • Clifford-algebraic neural networks Presented by international experts in the field, Complex-Valued Neural Networks: Advances and Applications is ideal for advanced-level computational intelligence theorists, electromagnetic theorists, and mathematicians interested in computational intelligence, artificial intelligence, machine learning theories, and algorithms.

An authoritative guide to computer simulation grounded in a multi-disciplinary approach for solving complex problems. “Simulation and Computational Red Teaming for Problem Solving” offers a review of computer simulation that is grounded in a multi-disciplinary approach. The authors present the theoretical foundations of simulation and modeling paradigms from the perspective of an analyst. The book provides the fundamental background information needed for designing and developing consistent and useful simulations. In addition to this basic information, the authors explore several advanced topics. The book's advanced topics demonstrate how modern artificial intelligence and computational intelligence concepts and techniques can be combined with various simulation paradigms for solving complex and critical problems. Authors examine the concept of “Computational Red Teaming” to reveal how the combined fundamentals and advanced techniques are used successfully for solving and testing complex real-world problems. This important book: • Demonstrates how computer simulation and Computational Red Teaming support each other for solving complex problems • Describes the main approaches to modeling real-world phenomena and embedding these models into computer simulations • Explores how a number of advanced artificial intelligence and computational intelligence concepts are used in conjunction with the fundamental aspects of simulation Written for researchers and students in the computational modelling and data analysis fields, “Simulation and Computational Red Teaming for Problem Solving” covers the foundation and the standard elements of the process of building a simulation and explores the simulation topic with a modern research approach.

A thorough look at how societies can use cultural algorithms to understand human social evolution For those working in computational intelligence, developing an understanding of how cultural algorithms and social intelligence form the essential framework for the evolution of human social interaction is essential. This book, “Cultural Algorithms: Tools to Model Complex Dynamic Social Systems”, is the foundation of that study. It showcases how we can use cultural algorithms to organize social structures and develop socio-political systems that work. For such a vast topic, the text covers everything from the history of the development of cultural algorithms and the basic framework with which it was organized. Readers will also learn how other nature-inspired algorithms can be expressed and how to use social metrics to assess the performance of various algorithms. In addition to these topics, the book covers topics including: • The CAT system including the Repast Simphony System and CAT Sample Runs • How to problem solve using social networks in cultural algorithms with auctions • Understanding Common Value Action to enhance Social Knowledge Distribution Systems • Case studies on team formations • An exploration of virtual worlds using cultural algorithms For industry professionals or new students, “Cultural Algorithms” provides an impactful and thorough look at both social intelligence and how human social evolution translates into the modern world.

An introductory book that provides theoretical, practical, and application coverage of the emerging field of type-2 fuzzy logic control Until recently, little was known about type-2 fuzzy controllers due to the lack of basic calculation methods available for type-2 fuzzy sets and logic-and many different aspects of type-2 fuzzy control still needed to be investigated in order to advance this new and powerful technology. This self-contained reference covers everything readers need to know about the growing field. Written with an educational focus in mind, “Introduction to Type-2 Fuzzy Logic Control: Theory and Applications” uses a coherent structure and uniform mathematical notations to link chapters that are closely related, reflecting the book's central themes: analysis and design of type-2 fuzzy control systems. The book includes worked examples, experiment and simulation results, and comprehensive reference materials. The book also offers downloadable computer programs from an associated website. Presented by world-class leaders in type-2 fuzzy logic control, Introduction to Type-2 Fuzzy Logic Control: • Is useful for any technical person interested in learning type-2 fuzzy control theory and its applications • Offers experiment and simulation results via downloadable computer programs • Features type-2 fuzzy logic background chapters to make the book self-contained • Provides an extensive literature survey on both fuzzy logic and related type-2 fuzzy control “Introduction to Type-2 Fuzzy Logic Control” is an easy-to-read reference book suitable for engineers, researchers, and graduate students who want to gain deep insight into type-2 fuzzy logic control.

A new approach to unsupervised learning Evolving technologies have brought about an explosion of information in recent years, but the question of how such information might be effectively harvested, archived, and analyzed remains a monumental challenge-for the processing of such information is often fraught with the need for conceptual interpretation: a relatively simple task for humans, yet an arduous one for computers. Inspired by the relative success of existing popular research on self-organizing neural networks for data clustering and feature extraction, “Unsupervised Learning: A Dynamic Approach” presents information within the family of generative, self-organizing maps, such as the self-organizing tree map (SOTM) and the more advanced self-organizing hierarchical variance map (SOHVM). It covers a series of pertinent, real-world applications with regard to the processing of multimedia data-from its role in generic image processing techniques, such as the automated modeling and removal of impulse noise in digital images, to problems in digital asset management and its various roles in feature extraction, visual enhancement, segmentation, and analysis of microbiological image data. Self-organization concepts and applications discussed include: • Distance metrics for unsupervised clustering • Synaptic self-amplification and competition • Image retrieval • Impulse noise removal • Microbiological image analysis “Unsupervised Learning: A Dynamic Approach” introduces a new family of unsupervised algorithms that have a basis in self-organization, making it an invaluable resource for researchers, engineers, and scientists who want to create systems that effectively model oppressive volumes of data with little or no user intervention.