Computational Intelligence:

Concept to Implementation

        Table of Contents

Back to Home

Chapter 1 Chapter 2 Chapter 3 Chapter 4 Chapter 5 Chapter 6 Chapter 7 Chapter 8 Chapter 9 Chapter 10 Chapter 11 Chapter 12

Chapter 1 – Background presents definitions of terms that will be used throughout the book. It briefly reviews biological and behavioral motivations for the constituent methodologies of computational intelligence. The major application areas for each of the constituent methodologies, as well as of computational intelligence, are briefly reviewed.
BACK

Chapter 2 – Computational Intelligence, launches the reader directly into the core subject of the book. Rather than wait until evolutionary computation, neural networks, and fuzzy systems are all presented and discussed, and we pull them all together, we have chosen to immerse the reader directly into the computational intelligence milieu. We first review the concepts of adaptation and self-organization, key to our view of computational intelligence. Then we summarize the brief history of the computational intelligence field, viewing it from the perspectives of other researchers. This leads us into a discussion of our view of the relationships among the three major components and how they cooperate and/or are integrated into a computational intelligence system. We present our definition of computational intelligence, supported by diagrams that place it into context.

The next section of the book comprises “backbone” chapters on each of the three main constituents of computational intelligence: evolutionary computation, neural networks, and fuzzy logic, in that order. This order provides an initial focus on evolutionary computation, which is presented as providing a foundation for development of computational intelligence tools involving neural networks and fuzzy logic. When neural networks are discussed, we see how evolutionary computation can be used to evolve the weights and structure of feed-forward neural networks. When we get to fuzzy logic, we examine evolutionary computation applications to tools built using fuzzy logic. In other words, the evolutionary computation theme pervades the book.

A chapter discussing implementation issues and examples follows each backbone chapter. Each implementation chapter contains a section on implementation issues that addresses the following three subjects: 1) Features that are frequently incorporated into these implementations, 2) The features we chose and why, and, 3) Guidelines with respect to using them, including consideration of interactions among them. The implementation chapters are intended to provide the insight to go beyond "canned" applications with commercial software packages, and to provide a more thorough understanding of software and hardware implementation issues for computational intelligence paradigms.

Information on the history of computational intelligence, evolutionary computation, neural networks, and fuzzy logic is distributed among the corresponding backbone chapters. This is intended to facilitate continuity, and reflects the way we present the material in the classroom.
BACK

Chapter 3 -- Evolutionary Computation, has been adapted from the Evolutionary Computation Theory and Paradigms chapter in Swarm Intelligence (Kennedy, Eberhart and Shi, 2001) with updates and augmentations, including recent developments in particle swarm optimization and other evolutionary computation approaches. After reviewing the history of evolutionary computation, and giving an overview of the field, we discuss each of the main paradigms of evolutionary computation: genetic algorithms, evolutionary programming, evolution strategies, genetic programming, and particle swarm optimization.
BACK

Chapter 4 – Evolutionary Computation Implementations, discusses issues to be considered when implementing evolutionary computation paradigms, and presents two implementation examples: a "plain vanilla" genetic algorithm, and the real-valued particle swarm. The particle swarm optimization implementation can be run as a single particle swarm, or in a multi-swarm mode.
BACK

Chapter 5 – Artificial Neural Networks, first briefly overviews the history of neural networks, then examines what they are and why they are useful. Next is a discussion of neural network components and terminology, and a review of neural network topologies. A more detailed look at neural network learning and recall follows, focusing on three of the most commonly used neural network paradigms: backpropagation, learning vector quantization, and self-organizing feature map networks. These networks also represent the two basic learning types, supervised learning (backpropagation) and unsupervised learning (learning vector quantization and self-organizing feature maps). Hybrid networks and recurrent networks are briefly discussed. Finally, the issues of pre-processing and post-processing are examined.
BACK

Chapter 6 – Neural Network Implementations, discusses issues to be considered when implementing artificial neural networks, and presents four implementation examples: backpropagation, learning vector quantization, self-organizing feature maps, and evolutionary neural networks.
BACK

Chapter 7- Fuzzy Systems, Fuzzy Systems, leads off with a brief review of the history of the field, followed by an examination of fuzzy sets and fuzzy logic, the concepts of fuzzy sets, and approximate reasoning. The differences between fuzzy logic and probability are stressed. Both Mamdani and Takagi-Sugeno approaches to the design and analysis of fuzzy systems are presented. The chapter concludes by looking at some issues and special topics related to fuzzy systems.
BACK

Chapter 8 – Fuzzy System Implementations, discusses issues to be considered when implementing fuzzy systems, and presents two implementation examples: a traditional fuzzy rule system, and an evolutionary fuzzy system. It is with the evolutionary fuzzy system that we begin the transition into computational intelligence systems.
BACK

Chapter 9 – Computational Intelligence Implementations, reflects recent developments in the field, including evolutionary fuzzy systems and approaches to system adaptation using computational intelligence. The interaction and cooperation among the three basic components of computational intelligence will be expanded and a section on adaptive evolutionary computation using fuzzy systems and/or neural networks will be included. The role of non-linear dynamics (chaos theory) in computational intelligence is emphasized. Included will be material on recent developments in "edge of chaos" research and development that focuses on complex systems.
BACK

Chapter 10 – Performance Metrics, includes a number of system performance measures not generally used in other disciplines. Included are percent correct, sum-squared error, absolute error, normalized error, receiver operating characteristic curves. recall and precision, confusion matrices, and the chi-squared test.
BACK

Chapter 11 – Analysis and Explanation, presents several tools that are helpful in assessing and explaining how well a computational intelligence tool is doing its job. Included are sensitivity analyses, Hinton diagrams for neural networks, and the use of evolutionary computing tools for analysis. An example of using particle swarm to develop an explanation facility is included in this chapter.
BACK

Chapter 12 – Case Study Summaries, provides examples of practical applications. Two case studies are based on recent work by the authors, including one on human tremor analysis and another on optimization of logistics operations. Other case studies discussed in detail are schedule optimization and control system design. Several other case study examples are briefly reviewed. Software and datasets that support selected case studies are on the book's web site.
BACK