Fundamentals of Computational Intelligence: Neural Networks, Fuzzy Systems, and Evolutionary Computation -- Table of Contents -- Acknowledgments -- Chapter 1: Introduction to Computational Intelligence -- 1.1 Welcome to Computational Intelligence -- 1.2 What Makes This Book Special -- 1.3 What This Book Covers -- 1.4 How to Use This Book -- 1.5 Final Thoughts Before You Get Started -- Part I: Neural Networks -- Chapter 2: Introduction and Single-Layer Neural Networks -- 2.1 Short History of Neural Networks -- 2.2 Rosenblatt's Neuron -- 2.3 Perceptron Training Algorithm -- 2.3.1 Test Problem -- 2.3.2 Constructing Learning Rules -- 2.3.3 Unified Learning Rule -- 2.3.4 Training Multiple-Neuron Perceptrons -- 2.3.4.1 Problem Statement -- 2.4 The Perceptron Convergence Theorem -- 2.5 Computer Experiment Using Perceptrons -- 2.6 Activation Functions -- 2.6.1 Threshold Function -- 2.6.2 Sigmoid Function -- Exercises -- Chapter 3: Multilayer Neural Networks and Backpropagation -- 3.1 Universal Approximation Theory -- 3.2 The Backpropagation Training Algorithm -- 3.2.1 The Description of the Algorithm -- 3.2.2 The Strategy for Improving the Algorithm -- 3.2.3 The Design Procedure of the Algorithm -- 3.3 Batch Learning and Online Learning -- 3.3.1 Batch Learning -- 3.3.2 Online Learning -- 3.4 Cross-Validation and Generalization -- 3.4.1 Cross-Validation -- 3.4.2 Generalization -- 3.4.3 Convolutional Neural Networks -- 3.5 Computer Experiment Using Backpropagation -- Exercises -- Chapter 4: Radial-Basis Function Networks -- 4.1 Radial-Basis Functions -- 4.2 The Interpolation Problem -- 4.3 Training Algorithms for Radial-Basis Function Networks -- 4.3.1 Layered Structure of a Radial-Basis Function Network -- 4.3.2 Modification of the Structure of RBF Network -- 4.3.3 Hybrid Learning Process -- 4.4 Universal Approximation -- 4.5 Kernel Regression.

Exercises -- Chapter 5: Recurrent Neural Networks -- 5.1 The Hopfield Network -- 5.2 The Grossberg Network -- 5.2.1 Basic Nonlinear Model -- 5.2.2 Two-Layer Competitive Network -- 5.2.2.1 Layer 1 -- 5.2.2.2 Layer 2 -- 5.2.2.3 Learning Law -- Basic Nonlinear Model: Leaky Integrator -- Layer 1 -- Layer 2 -- 5.3 Cellular Neural Networks -- 5.4 Neurodynamics and Optimization -- 5.5 Stability Analysis of Recurrent Neural Networks -- 5.5.1 Stability Analysis of the Hopfield Network -- 5.5.2 Stability Analysis of the Cohen-Grossberg Network -- Exercises -- Part II: Fuzzy Set Theory and Fuzzy Logic -- Chapter 6: Basic Fuzzy Set Theory -- 6.1 Introduction -- 6.2 A Brief History -- 6.3 Fuzzy Membership Functions and Operators -- 6.3.1 Membership Functions -- 6.3.2 Basic Fuzzy Set Operators -- 6.4 Alpha-Cuts, the Decomposition Theorem, and the Extension Principle -- 6.5 Compensatory Operators -- 6.6 Conclusions -- Exercises -- Chapter 7: Fuzzy Relations and Fuzzy Logic Inference -- 7.1 Introduction -- 7.2 Fuzzy Relations and Propositions -- 7.3 Fuzzy Logic Inference -- 7.4 Fuzzy Logic for Real-Valued Inputs -- 7.5 Where Do the Rules Come From? -- 7.6 Chapter Summary -- Exercises -- Chapter 8: Fuzzy Clustering and Classification -- 8.1 Introduction to Fuzzy Clustering -- 8.2 Fuzzy c-Means -- 8.3 An Extension of the Fuzzy c-Means -- 8.4 Possibilistic c-Means -- 8.5 Fuzzy Classifiers: Fuzzy k-Nearest Neighbors -- 8.6 Chapter Summary -- Exercises -- Chapter 9: Fuzzy Measures and Fuzzy Integrals -- 9.1 Fuzzy Measures -- 9.2 Fuzzy Integrals -- 9.3 Training the Fuzzy Integrals -- 9.4 Summary and Final Thoughts -- Exercises -- Part III: Evolutionary Computation -- Chapter 10: Evolutionary Computation -- 10.1 Basic Ideas and Fundamentals -- 10.2 Evolutionary Algorithms: Generate and Test -- 10.3 Representation, Search, and Selection Operators.

10.4 Major Research and Application Areas -- 10.4.1 Optimization -- 10.4.2 Design -- 10.4.3 Learning and Games -- 10.4.4 Theory -- 10.5 Summary -- Exercises -- Chapter 11: Evolutionary Optimization -- 11.1 Global Numerical Optimization -- 11.1.1 A Canonical Example in One Dimension -- 11.1.2 A Canonical Example in Two or More Dimensions -- 11.1.3 Evolution versus Gradient Methods -- 11.2 Combinatorial Optimization -- 11.3 Some Mathematical Considerations -- 11.3.1 Convergence -- 11.3.2 Representation -- 11.3.3 Selection -- 11.3.4 Variation -- 11.4 Constraint Handling -- 11.5 Self-Adaptation -- 11.5.1 The 1/5 Rule -- 11.5.2 Meta-Evolution on Real-Valued Parameters -- 11.5.3 Meta-Evolution on Probabilities of Variation Operators -- 11.5.4 Meta-Evolution on Combinations of Variation Operators -- 11.5.5 Fitness Distributions of Variation Operators -- 11.6 Summary -- Exercises -- Chapter 12: Evolutionary Learning and Problem Solving -- 12.1 Evolving Parameters of a Regression Equation -- 12.1.1 A Canonical Example -- 12.1.2 Objectives Other Than Least Mean Squared Error -- 12.2 Evolving the Structure and Parameters of Input-Output Systems -- 12.2.1 Evolving ARMA(X) Models -- 12.2.2 Evolving Neural Networks -- 12.2.3 Evolving Multiple Interacting Programs as Networks -- 12.2.4 Summary -- 12.3 Evolving Clusters -- 12.3.1 Evolutionary Information: Theoretic Clustering with Rotatable Hyperboxes -- 12.4 Evolutionary Classification Models -- 12.4.1 Evolving Neural Networks -- 12.4.2 Evolving Rules -- 12.5 Evolutionary Control Systems -- 12.5.1 Cart-Pole Systems -- 12.5.2 Truck Backer-Upper -- 12.6 Evolutionary Games -- 12.6.1 Iterated Prisoner's Dilemma -- 12.6.2 Board Games and Video Games -- 12.7 Summary -- Exercises -- Chapter 13: Collective Intelligence and Other Extensions of Evolutionary Computation -- 13.1 Particle Swarm Optimization.

13.2 Differential Evolution -- 13.3 Ant Colony Optimization -- 13.4 Evolvable Hardware -- 13.5 Interactive Evolutionary Computation -- 13.6 Multicriteria Evolutionary Optimization -- 13.7 Summary -- Exercises -- References -- Index -- IEEE Press Series on: Computational Intelligence -- End User License Agreement.

Description based on publisher supplied metadata and other sources.

Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2022. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.