Fundamentals of Computational Intelligence: Neural Networks, Fuzzy Systems, and Evolutionary Computation

Provides an in-depth and even treatment of the three pillars of computational intelligence and how they relate to one another  This book covers the three fundamental topics that form the basis of computational intelligence:  neural networks, fuzzy systems, and evolutionary computation. The text focuses on inspiration, design, theory, and practical aspects of implementing procedures to solve real-world problems. While other books in the three fields that comprise computational intelligence are written by specialists in one discipline, this book is co-written by current former Editor-in-Chief of IEEE Transactions on Neural Networks and Learning Systems, a former Editor-in-Chief of IEEE Transactions on Fuzzy Systems, and the founding Editor-in-Chief of IEEE Transactions on Evolutionary Computation. The coverage across the three topics is both uniform and consistent in style and notation. Discusses single-layer and multilayer neural networks, radial-basis function networks, and recurrent neural networks Covers fuzzy set theory, fuzzy relations, fuzzy logic interference, fuzzy clustering and classification, fuzzy measures and fuzzy integrals Examines evolutionary optimization, evolutionary learning and problem solving, and collective intelligence Includes end-of-chapter practice problems that will help readers apply methods and techniques to real-world problems Fundamentals of Computational intelligence is written for advanced undergraduates, graduate students, and practitioners in electrical and computer engineering, computer science, and other engineering disciplines.

Table of Contents:
Acknowledgments xi 1. Introduction to Computational Intelligence 1 1.1 Welcome to Computational Intelligence 1 1.2 What Makes This Book Special 1 1.3 What This Book Covers 2 1.4 How to Use This Book 2 1.5 Final Thoughts Before You Get Started 3 PART I NEURAL NETWORKS 5 2. Introduction and Single-Layer Neural Networks 7 2.1 Short History of Neural Networks 9 2.2 Rosenblatt’s Neuron 10 2.3 Perceptron Training Algorithm 13 2.4 The Perceptron Convergence Theorem 23 2.5 Computer Experiment Using Perceptrons 25 2.6 Activation Functions 28 Exercises 30 3. Multilayer Neural Networks and Backpropagation 35 3.1 Universal Approximation Theory 35 3.2 The Backpropagation Training Algorithm 37 3.3 Batch Learning and Online Learning 45 3.4 Cross-Validation and Generalization 47 3.5 Computer Experiment Using Backpropagation 53 Exercises 56 4. Radial-Basis Function Networks 61 4.1 Radial-Basis Functions 61 4.2 The Interpolation Problem 62 4.3 Training Algorithms For Radial-Basis Function Networks 64 4.4 Universal Approximation 69 4.5 Kernel Regression 70 Exercises 75 5. Recurrent Neural Networks 77 5.1 The Hopfield Network 77 5.2 The Grossberg Network 81 5.3 Cellular Neural Networks 88 5.4 Neurodynamics and Optimization 91 5.5 Stability Analysis of Recurrent Neural Networks 93 Exercises 99 PART II FUZZY SET THEORY AND FUZZY LOGIC 101 6. Basic Fuzzy Set Theory 103 6.1 Introduction 103 6.2 A Brief History 107 6.3 Fuzzy Membership Functions and Operators 108 6.4 Alpha-Cuts, The Decomposition Theorem, and The Extension Principle 117 6.5 Compensatory Operators 120 6.6 Conclusions 124 Exercises 124 7. Fuzzy Relations and Fuzzy Logic Inference 127 7.1 Introduction 127 7.2 Fuzzy Relations and Propositions 128 7.3 Fuzzy Logic Inference 131 7.4 Fuzzy Logic For Real-Valued Inputs 135 7.5 Where Do The Rules Come From? 138 7.6 Chapter Summary 142 Exercises 143 8. Fuzzy Clustering and Classification 147 8.1 Introduction to Fuzzy Clustering 147 8.2 Fuzzy c-Means 155 8.3 An Extension of The Fuzzy c-Means 167 8.4 Possibilistic c-Means 169 8.5 Fuzzy Classifiers: Fuzzy k-Nearest Neighbors 174 8.6 Chapter Summary 179 Exercises 180 9. Fuzzy Measures and Fuzzy Integrals 183 9.1 Fuzzy Measures 183 9.2 Fuzzy Integrals 188 9.3 Training The Fuzzy Integrals 191 9.4 Summary and Final Thoughts 203 Exercises 203 PART III EVOLUTIONARY COMPUTATION 207 10. Evolutionary Computation 209 10.1 Basic Ideas and Fundamentals 209 10.2 Evolutionary Algorithms: Generate and Test 216 10.3 Representation, Search, and Selection Operators 221 10.4 Major Research and Application Areas 223 10.5 Summary 225 Exercises 225 11. Evolutionary Optimization 227 11.1 Global Numerical Optimization 229 11.2 Combinatorial Optimization 233 11.3 Some Mathematical Considerations 238 11.4 Constraint Handling 255 11.5 Self-Adaptation 258 11.6 Summary 264 Exercises 265 12. Evolutionary Learning and Problem Solving 269 12.1 Evolving Parameters of A Regression Equation 270 12.2 Evolving The Structure and Parameters of Input–Output Systems 274 12.3 Evolving Clusters 292 12.4 Evolutionary Classification Models 298 12.5 Evolutionary Control Systems 307 12.6 Evolutionary Games 314 12.7 Summary 320 Exercises 321 13. Collective Intelligence and Other Extensions of Evolutionary Computation 323 13.1 Particle Swarm Optimization 323 13.2 Differential Evolution 326 13.3 Ant Colony Optimization 329 13.4 Evolvable Hardware 331 13.5 Interactive Evolutionary Computation 333 13.6 Multicriteria Evolutionary Optimization 335 13.7 Summary 340 Exercises 340 References 343 Index 361