Details

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

<p><b>James Keller</b> holds the University of Missouri Curators' Professorship in the Electrical and Computer Engineering and Computer Science Departments on the Columbia Campus, and is the R.L. Tatum Professor in the College of Engineering. Dr. Keller is a Life Fellow of the IEEE, a Fellow of the International Fuzzy Systems Association, and a former president of the North American Fuzzy Information Processing Society.</p> <p><b>Derong Liu</b> is a Professor of Electrical and Computer Engineering at the University of Illinois at Chicago, USA, and a Professor of Automation and Electrical Engineering at the University of Science and Technology Beijing, China. Dr. Liu is a Fellow of the IEEE and a Fellow of the International Neural Network Society. He has published 17 books, including <i>Reinforcement Learning and Approximate Dynamic Programming for Feedback Control</i> (2012, Wiley-IEEE Press). He is the Editor-in-Chief of Artificial Intelligence Review, and he served as the Editor-in-Chief of the IEEE Transactions on Neural Networks and Learning Systems (2010-2015).</p> <p><b>David Fogel</b> is the President of Natural Selection, Inc., CEO of Natural Selection Financial, Inc., a Fellow of the IEEE, and the series editor for the Wiley-IEEE Press Series on Computational Intelligence. Dr. Fogel has 30 years of experience pioneering contributions in the field of computational intelligence, and is co-inventor of the EffectCheck® sentiment analysis system. He has written several books including <i>Evolutionary Computation: The Fossil Record</i> (1998) and <i>Evolutionary Computation Toward a New Philosophy of Machine Intelligence, 3rd Edition</i> (2005), both published by the Wiley-IEEE Press.</p>

<p><b>Provides an in-depth and even treatment of the three pillars of computational intelligence and how they relate to one another</b></p> <p>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.</p> <ul> <li>Discusses single-layer and multilayer neural networks, radial-basis function networks, and recurrent neural networks</li> <li>Covers fuzzy set theory, fuzzy relations, fuzzy logic interference, fuzzy clustering and classification, fuzzy measures and fuzzy integrals</li> <li>Examines evolutionary optimization, evolutionary learning and problem solving, and collective intelligence</li> <li>Includes end-of-chapter practice problems that will help readers apply methods and techniques to real-world problems</li> </ul> <p><i>Fundamentals of Computational intelligence</i> is written for advanced undergraduates, graduate students, and practitioners in electrical and computer engineering, computer science, and other engineering disciplines.</p>

US