Keller, James M.,
Fundamentals of computational intelligence : neural networks, fuzzy systems, and evolutionary computation / James M. Keller, Derong Liu, David B. Fogel. - 1 PDF (400 pages). - IEEE Press series on computational intelligence . - IEEE series on computational intelligence. .
Includes bibliographical references and index.
Chapter 6: Basic Fuzzy Set Theory6.1 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 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 Rules2.3.3 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 Learning3.3.1 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 RegressionExercises; 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
Restricted to subscribers or individual electronic text purchasers.
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.
Mode of access: World Wide Web
1119214408 9781119214403
Expert systems (Computer science)
Expert systems (Computer science)
Electronic books.
QA76.76.E95 / K45 2016eb
006.33
Fundamentals of computational intelligence : neural networks, fuzzy systems, and evolutionary computation / James M. Keller, Derong Liu, David B. Fogel. - 1 PDF (400 pages). - IEEE Press series on computational intelligence . - IEEE series on computational intelligence. .
Includes bibliographical references and index.
Chapter 6: Basic Fuzzy Set Theory6.1 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 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 Rules2.3.3 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 Learning3.3.1 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 RegressionExercises; 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
Restricted to subscribers or individual electronic text purchasers.
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.
Mode of access: World Wide Web
1119214408 9781119214403
Expert systems (Computer science)
Expert systems (Computer science)
Electronic books.
QA76.76.E95 / K45 2016eb
006.33