Fuzzy neural networks for real time control applications : concepts, modeling and algorithms for fast learning /

Mostrar otras versiones (1)

AN INDISPENSABLE RESOURCE FOR ALL THOSE WHO DESIGN AND IMPLEMENT TYPE-1 AND TYPE-2 FUZZY NEURAL NETWORKS IN REAL TIME SYSTEMS Delve into the type-2 fuzzy logic systems and become engrossed in the parameter update algorithms for type-1 and type-2 fuzzy neural networks and their stability analysis wit...

Descripción completa

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autores principales: Kayacan, Erdal (Autor), Khanesar, Mojtaba Ahmadieh (Autor)
Otros Autores: Mendel, Jerry M. (author of foreword.)
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Amsterdam : Butterworth-Heinemann is an imprint of Elsevier, [2015].
Temas:
Neural networks (Computer science)
Fuzzy systems.
Réseaux neuronaux (Informatique)
Systèmes flous.
COMPUTERS / General
Fuzzy systems
Acceso en línea:Texto completo (Requiere registro previo con correo institucional)
Tabla de Contenidos:
  • Front Cover; Fuzzy Neural Networks Forreal Time Control Applications: Concepts, Modeling and Algorithms for Fast Learning; Copyright; Dedication; Contents; Foreword; References; Preface; Acknowledgments; List of Acronyms/Abbreviations; Chapter 1: Mathematical Preliminaries; 1.1 Introduction; 1.2 Linear Matrix Algebra; 1.3 Function; 1.4 Stability Analysis; 1.5 Sliding Mode Control Theory; 1.6 Conclusion; References; Chapter 2: Fundamentals of Type-1 Fuzzy Logic Theory; 2.1 Introduction; 2.2 Type-1 Fuzzy Sets; 2.3 Basics of Fuzzy Logic Control; 2.3.1 FLC Block Diagram; 2.3.1.1 Fuzzification
  • 2.3.1.2 Rule Base2.3.1.3 Inference; 2.3.1.4 Defuzzification; 2.4 Pros and Cons of Fuzzy Logic Control; 2.5 Western and Eastern Perspectives on Fuzzy Logic; 2.6 Conclusion; References; Chapter 3: Fundamentals of Type-2 Fuzzy Logic Theory; 3.1 Introduction; 3.2 Type-2 Fuzzy Sets; 3.2.1 Interval Type-2 Fuzzy Sets; 3.2.2 T2FLS Block Diagram; 3.2.2.1 Fuzzifier; 3.2.2.2 Rule Base; 3.2.2.3 Inference; 3.2.2.4 Type Reduction; 3.2.2.5 Defuzzification; 3.3 Existing Type-2 Membership Functions; 3.3.1 A Novel Type-2 MF: Elliptic MF; 3.4 Conclusion; References; Chapter 4: Type-2 Fuzzy Neural Networks
  • 4.1 Type-1 Takagi-Sugeno-Kang Model4.2 Other Takagi-Sugeno-Kang Models; 4.2.1 Model I; 4.2.2 Model II; 4.2.2.1 Interval Type-2 TSK FLS; 4.2.2.2 Numerical Example of the Interval Type-2 TSK FLS; 4.2.3 Model III; 4.3 Conclusion; References; Chapter 5: Gradient Descent Methods for Type-2 Fuzzy Neural Networks; 5.1 Introduction; 5.2 Overview of Iterative Gradient Descent Methods; 5.2.1 Basic Gradient-Descent Optimization Algorithm; 5.2.2 Newton and Gauss-Newton Optimization Algorithms; 5.2.3 LM Algorithm; 5.2.4 Gradient Descent Algorithm with an Adaptive Learning Rate
  • 5.2.5 GD Algorithm with a Momentum Term5.3 Gradient Descent Based Learning Algorithms for Type-2 Fuzzy Neural Networks; 5.3.1 Consequent Part Parameters; 5.3.2 Premise Part Parameters; 5.3.3 Variants of the Back-Propagation Algorithm for Training the T2FNNs; 5.4 Stability Analysis; 5.4.1 Stability Analysis of GD for Training of T2FNN; 5.4.2 Stability Analysis of the LM for Training of T2FNN; 5.5 Further Reading; 5.6 Conclusion; References; Chapter 6: Extended Kalman Filter Algorithm for the Tuning of Type-2 Fuzzy Neural Networks; 6.1 Introduction; 6.2 Discrete Time Kalman Filter

Ejemplares similares