Cargando…
Diffuse algorithms for neural and neuro-fuzzy networks : with applications in control engineering and signal processing /
"Diffuse Algorithms for Neural and Neuro-Fuzzy Networks: With Applications in Control Engineering and Signal Processing presents new approaches to training neural and neuro-fuzzy networks. This book is divided into six chapters. Chapter 1 consists of plants models reviews, problems statements,...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Kidlington, Oxford, United Kingdom :
Butterworth-Heinemann is an imprint of Elsevier,
2017.
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Front Cover; Diffuse Algorithms for Neural and Neuro-Fuzzy Networks; Copyright Page; Contents; List of Figures; List of Tables; Preface; 1 Introduction; 1.1 Separable Models of Plants and Training Problems Associated With Them; 1.1.1 Separable Least Squares Method; 1.1.2 Perceptron With One Hidden Layer; 1.1.3 Radial Basis Neural Network; 1.1.4 Neuro-Fuzzy Network; 1.1.5 Plant Models With Time Delays; 1.1.6 Systems With Partly Unknown Dynamics; 1.1.7 Recurrent Neural Network; 1.1.8 Neurocontrol; 1.2 The Recursive Least Squares Algorithm With Diffuse and Soft Initializations.
- 1.3 Diffuse Initialization of the Kalman Filter2 Diffuse Algorithms for Estimating Parameters of Linear Regression; 2.1 Problem Statement; 2.2 Soft and Diffuse Initializations; 2.3 Examples of Application; 2.3.1 Identification of Nonlinear Dynamic Plants; 2.3.2 Supervisory Control; 2.3.3 Estimation With a Sliding Window; 3 Statistical Analysis of Fluctuations of Least Squares Algorithm on Finite Time Interval; 3.1 Problem Statement; 3.2 Properties of Normalized Root Mean Square Estimation Error; 3.3 Fluctuations of Estimates under Soft Initialization with Large Parameters.
- 3.4 Fluctuations Under Diffuse Initialization3.5 Fluctuations with Random Inputs; 4 Diffuse Neural and Neuro-Fuzzy Networks Training Algorithms; 4.1 Problem Statement; 4.2 Training With the Use of Soft and Diffuse Initializations; 4.3 Training in the Absence of a Priori Information About Parameters of the Output Layer; 4.4 Convergence of Diffuse Training Algorithms; 4.4.1 Finite Training Set; 4.4.2 Infinite Training Set; 4.5 Iterative Versions of Diffuse Training Algorithms; 4.6 Diffuse Training Algorithm of Recurrent Neural Network.
- 4.7 Analysis of Training Algorithms With Small Noise Measurements4.8 Examples of Application; 4.8.1 Identification of Nonlinear Static Plants; 4.8.2 Identification of Nonlinear Dynamic Plants; 4.8.3 Example of Classification Task; 5 Diffuse Kalman Filter; 5.1 Problem Statement; 5.2 Estimation With Diffuse Initialization; 5.3 Estimation in the Absence or Incomplete a Priori Information About Initial Conditions; 5.4 Systems State Recovery in a Finite Number of Steps; 5.5 Filtering With the Sliding Window; 5.6 Diffuse Analog of the Extended Kalman Filter; 5.7 Recurrent Neural Network Training.
- 5.8 Systems With Partly Unknown Dynamics6 Applications of Diffuse Algorithms; 6.1 Identification of the Mobile Robot Dynamics; 6.2 Modeling of Hysteretic Deformation by Neural Networks; 6.3 Harmonics Tracking of Electric Power Networks; Glossary; Notations; Abbreviations; References; Index; Back Cover.