Neural Networks and Learning Algorithms in MATLAB

Description

This book explains the basic concepts, theory and applications of neural networks in a simple unified approach with clear examples and simulations in the MATLAB programming language. The scripts herein are coded for general purposes to be easily extended to a variety of problems in different areas of application. They are vectorized and optimized to run faster and be applicable to high-dimensional engineering problems. This book will serve as a main reference for graduate and undergraduate courses in neural networks and applications. This book will also serve as a main basis for researchers dealing with complex problems that require neural networks for finding good solutions in areas, such as time series prediction, intelligent control and identification. In addition, the problem of designing neural network by using metaheuristics, such as the genetic algorithms and particle swarm optimization, with one objective and with multiple objectives, is presented. Preface Contents 1 Introduction 1.1 Overview 1.2 Some Applications of Neural Networks 1.3 Different Types of Neural Network Training 1.4 Learning Principles in Neural Networks References 2 Multilayer Perceptron (MLP) Neural Networks 2.1 Training Based on Error Backpropagation 2.2 Implementation in MATLAB 2.3 Application of Neural Network in Classification 2.4 Over-Parameterization 2.5 Over-Training 2.6 Training Based on Full Propagation References 3 Neural Networks Training Based on Recursive Least Squares (RLS) 3.1 RLS Training Technique 3.2 Implementation in MATLAB 3.3 Comparison with Gradient Descent 4 Neural Networks Training Based on Second-Order Optimization Technique 4.1 Introduction 4.2 Newton’s Method 4.3 Levenberg–Marquardt Algorithm 4.4 Conjugate Gradient (CG) Method 4.5 Implementation in MATLAB References 5 Neural Networks Training Based on Genetic Algorithm 5.1 Introduction 5.1.1 What is the Genetic Algorithm (GA)? 5.1.2 Operators of a Genetic Algorithm 5.1.3 Applications of Genetic Algorithm 5.2 Genetic Algorithm in MATLAB 5.3 Optimization of Neural Network Parameters Based on Genetic Algorithm Reference 6 Neural Network Training Based Particle Swarm Optimization (PSO) 6.1 Introduction 6.2 Algorithm Formulation 6.3 Implementation in MATLAB References 7 Neural Network Training Based on UKF 7.1 UKF Algorithm 7.2 Implementation in MATLAB References 8 Designing Neural-Fuzzy PID Controller Through Multiobjective Optimization 8.1 Introduction 8.2 Classic Methods 8.2.1 Ziegler–Nichols Method 8.2.2 Cohen-Coon Method 8.2.3 Smart Methods 8.2.4 Single-Objective Optimization 8.2.5 Multiobjective Optimization 8.2.6 Primary Definitions 8.2.7 Decision Variables 8.2.8 Constraints 8.2.9 Objective Functions 8.2.10 Dominance 8.2.11 Non-Dominated Set 8.2.12 Pareto Principle 8.2.13 Optimal Pareto Solution 8.2.14 Optimal Pareto Set 8.3 Objectives of Multiobjective Optimization 8.3.1 Common Algorithms in Solving Multiobjective Optimization 8.4 Designing Multiobjective PID Controller 8.5 Designing a MOPID Controller for a Sample Power System 8.5.1 First State 8.5.2 Second State 8.6 Using Fuzzy-Neural Network for Gain Schedule 8.7 Fuzzy-Neural Network Training for PID Controller Regulation 8.7.1 Simulation for Fuzzy-Neural Controller of Gain Schedule 8.8 Conclusion 8.9 Implementation in MATLAB 8.9.1 Dynamic Model of Power System 8.9.2 First Example 8.9.3 Supplementary Ideas on Modeling the Power System for the Frequency Load Problem Uncited Reference