\"MATLAB Neural Network Super Learning Manual\" is based on the recently launched MATLAB R2013a Neural Network Toolbox, and systematically and comprehensively introduces various concepts and applications of neural networks. \"MATLAB Neural Network Super Learning Manual\" is logically arranged and uses examples from beginning to end; the content is complete and each chapter is relatively independent. It is a rare learning book for mastering MATLAB neural networks. The book is divided into 16 chapters, starting with an introduction to MATLAB, and details the basic knowledge of MATLAB, MATLAB programming, an overview of artificial neural networks, perceptrons, linear neural networks, BP neural networks, RBF neural networks, feedback neural networks, competitive neural networks, applications of neural networks in Simulink, neural network GUI, custom neural networks and functions, etc. At the end of the book, it also introduces several application methods of neural networks in MATLAB in detail. \"MATLAB Neural Network Super Learning Manual\" takes the neural network structure as the main line and the learning algorithm as the secondary line, combined with various examples, the purpose is to make it easy for readers to understand and apply. This book is a comprehensive book that briefly introduces MATLAB neural network design skills. The MATLAB Neural Network Super Learning Manual is easy to understand, with examples and detailed explanations. It can be used as a textbook for graduate and undergraduate students in science and engineering in colleges and universities, and can also be used as a reference book for scientific research and engineering technicians. Series features The authors of this series are all experienced professional engineers. The content of the books is derived from the summary of the authors\' many years of work experience, with a unified cover design and a unified writing style. Whether it is the selection of cases, the level of detail of the explanations, or the professional knowledge involved in the book, the book fully considers the readers\' preferences and strives to create the long-selling brand of \"Detailed Analysis of Engineering Software Applications\" Chapter 1 Introduction to MATLAB 1.1 The development of MATLAB 1.2 The characteristics and application areas of MATLAB 1.3 Installation of MATLAB R2013a 1.4 Working environment of MATLAB R2013a 1.4.1 Introduction to the operating interface 1.4.2 Workspace (Command Window) 1.4.3 Command History (Command History Window) 1.4.4 Input variables 1.4.5 Path management 1.4.6 Search path 1.4.7 Workspace (Workspace) 1.4.8 Editing commands for variables 1.4.9 Accessing data files 1.5 Help system of MATLAB R2013a 1.5.1 Plain text help 1.5.2 Demonstration help 1.5.3 Help navigation 1.5.4 Help file directory window 1.5.5 Help file index window 1.6 Chapter SummaryChapter 2 MATLAB Basics2.1 Basic Concepts2.1.1 Overview of MATLAB Data Types2.1.2 Constants and Variables2.1.3 Scalars, Vectors, Matrices and Arrays2.1.4 Operators2.1.5 Commands, Functions, Expressions and Statements2.2 Arrays in MATLAB2.2.1 Saving and Loading Arrays2.2.2 Array Indexing and Addressing2.2.3 Expanding and Croping Arrays2.2.4 Changing the Shape of Arrays2.2.5 Array Operations2.2.6 Searching Arrays2.2.7 Sorting Arrays2.2.8 Dimensionality Reduction of High-Dimensional Arrays2.3 Curve Fitting2.3.1 Polynomial Fitting2.3.2 Principle and Example of Weighted Least Squares (WLS) Fitting2.4 M-Files2.4.1 Overview of M-Files2.4.2 Local Variables and Global Variables2.4.3 Editing and Running M-Files2.4.4 Script Files2.4.5 3.3.1 Keyboard input statement (input) 3.3.2 Screen output statement (disp) 3.3.3 M data file storage/load (save/load) 3.3.4 Formatted text file storage/read (fprintf/fscanf) 3.3.5 Binary data file storage/read (fwrite/fread) 3.3.6 3.5.1 Efficiency optimization (time optimization) 3.5.2 Memory optimization (space optimization) 3.5.3 Programming precautions 3.5.4 Algorithm programs of several common mathematical methods 3.6 Program debugging 3.6.1 Program debugging commands 3.6.2 Program analysis 3.7 Summary of this chapter Chapter 4 Overview of artificial neural networks 4.1 Artificial neural networks 4.1.1 The development of artificial neural networks 4.1.2 Research content of artificial neural networks 4.1.3 Research directions of artificial neural networks 4.1.4 Development trend of artificial neural networks 4.2 Neurons 4.2.1 Neuron cells 4.2.2 MP model 4.2.3 General neuron model 4.3 Neural network structure and learning 4.3.1 Neural network structure 4.3.2 Neural network learning 4.4 MATLAB Neural Network Toolbox 4.4.1 Neural Network Toolbox Function 4.4.2 Use of Neural Network Toolbox 4.5 Chapter SummaryChapter 5 Perceptron5.1 Perceptron Principle5.1.1 Perceptron Model5.1.2 Perceptron Initialization5.1.3 Perceptron Learning Rule5.1.4 Perceptron Training5.2 Limitations of Perceptron5.3 Perceptron Toolbox Functions5.4 MATLAB Simulation Program Design of Perceptron5.4.1 MATLAB Simulation Program Design of Single-layer Perceptron5.4.2 MATLAB Simulation Program Design of Multi-layer Perceptron5.5 Chapter SummaryChapter 6 Linear Neural Network6.1 Linear Neural Network Principle6.1.1 Linear Neural Network Model6.1.2 Linear Neural Network Initialization6.1.3 Linear Neural Network Learning Rule6.1.4 Linear Neural Network Training6.2 Linear Neural Network Toolbox Functions6.3 MATLAB Simulation Program Design of Linear Neural Network6.3.1 Basic Methods for Linear Neural Network Design6.3.2 Linear Neural Network Design6.4 Chapter SummaryChapter 7 BP Neural Network7.1 BP Neural Network Principle7.1.1 BP Neural Network Model7.1.2 BP Neural Network Algorithm7.1.3 7.1.1 RBF Neural Network Model 8.1.2 RBF Neural Network Working Principle 8.1.3 RBF Neural Network Implementation 8.2 RBF Neural Network Learning Algorithm 8.3 RBF Network Toolbox Function 8.3.1 RBF Toolbox Function 8.3.2 Conversion Function 8.3.3 Transfer Function 8.4 Nonlinear Filtering Based on RBF Network 8.4.1 Nonlinear filtering 8.4.2 RBF neural network for nonlinear filtering 8.5 MATLAB application examples of RBF network 8.6 Chapter summary Chapter 9 Feedback neural network 9.1 Basic concepts of feedback neural network 9.2 Hopfield network model 9.2.1 Hopfield network model 9.2.2 State trajectory 9.2.3 State trajectory divergence 9.3 Hopfield network toolbox function 9.3.1 Hopfield network creation function 9.3.2 Hopfield network transfer function 9.4 Discrete Hopfield network 9.4.1 DHNN model structure 9.4.2 Associative memory 9.4.3 Hebb learning rule of DHNN 9.4.4 Other methods of DHNN weight design 9.5 Continuous Hopfield network 9.6 Elman network 9.6.1 Elman network structure 9.6.2 Elman network creation function 9.6.3 Engineering application of Elman network 9.7 Summary of this chapter Chapter 10 Competitive neural network 10.1 Self-organizing competitive neural network 10.1.1 Several associative learning rules 10.1.2 Network structure 10.1.3 Principles of self-organizing neural network 10.1.4 Competitive learning rule 10.1.5 Training process of competitive network 10.2 10.2.1 Self-Organizing Feature Map Neural Network Topology 10.2.2 SOM Weight Adjustment Domain 10.2.3 SOM Network Operation Principle 10.2.4 Network Training Process 10.3 Adaptive Resonance Theory Neural Network 10.3.1 Overview of Adaptive Resonance Theory Neural Network 10.3.2 Structure and Characteristics of ART Network 10.4 Learning Vector Quantization Neural Network 10.4.1 LVQ Neural Network Structure 10.4.2 LVQ Neural Network Algorithm 10.5 Competitive Neural Network Toolbox Function 10.6 Application of Competitive Neural Network 10.7 Summary of this Chapter Chapter 11 Simulink Application of Neural Network 11.1 Neural Network Module Based on Simulink 11.1.1 Neural Network Module 11.1.2 Module Generation 11.2 Neural Network Control System Based on Simulink 11.2.1 Neural Network Model Predictive Control 11.2.2 Feedback Linearization Control 11.2.3 Model Reference Control 11.3 Summary of this Chapter Chapter 12 Neural Network GUI 12.1 GUI Introduction 12.1.1 GUI Design Tools 12.1.2 Starting GUIDE 12.1.3 Adding Control Components 12.1.4 Setting Control Component Properties 12.1.5 Writing Corresponding Program Code 12.1.6 Notes on Creating GUIs with GUIDE 12.1.7 Customizing Standard Menus 12.2 Neural Network GUI 12.2.1 Conventional Neural Network GUI 12.2.2 Neural Network Fitting GUI 12.2.3 Neural Network Pattern Recognition GUI 12.2.4 Neural Network Clustering GUI 12.3 GUI Data Operation 12.3.1 Importing Data from Workspace to GUI 12.3.2 Exporting Data from GUI to Workspace 12.3.3 Storing and Reading Data 12.3.4 Deleting Data 12.4 Summary of This Chapter Chapter 13 Custom Neural Networks and Functions 13.1 Custom Neural Networks 13.1.1 Creating a Network 13.1.2 Initializing, Training, and Simulating a Network 13.2 13.2.1 The basic idea of random neural network 13.2.2 The simulated annealing algorithm 14.2.2 The simulated annealing algorithm is used for combinatorial optimization problems 14.2.3 Parameter control of annealing algorithm 14.3 Boltzmann machine 14.3.1 The network structure of Boltzmann machine 14.3.2 The working principle of Boltzmann machine 14.3.3 The operation steps of Boltzmann machine 14.3.4 The learning rule of Boltzmann machine 14.3.5 The improvement of Boltzmann machine 14.4 The application of random neural network 14.5 The summary of this chapter Chapter 15 Basic application of neural network 15.1 The application of perceptron neural network 15.2 The application of linear neural network 15.3 The application of BP neural network 15.4 The application of RBF neural network 15.5 Chapter SummaryChapter 16 Comprehensive Application of Neural Networks16.1 Application of BP Neural Networks16.1.1 Data Fitting16.1.2 Data Prediction16.1.3 Function Approximation16.2 PID Neural Network Control16.3 Genetic Algorithm Optimization of Neural Networks16.4 Fuzzy Neural Network Control16.5 Probabilistic Neural Network Classification Prediction16.6 Chapter SummaryAppendixReferences2 Application of simulated annealing algorithm to combinatorial optimization problem14.2.3 Parameter control of annealing algorithm14.3 Boltzmann machine14.3.1 Network structure of Boltzmann machine14.3.2 Working principle of Boltzmann machine14.3.3 Operation steps of Boltzmann machine14.3.4 Learning rule of Boltzmann machine14.3.5 Improvement of Boltzmann machine14.4 Application of random neural network14.5 Summary of this chapterChapter 15 Basic application of neural network15.1 Application of perceptron neural network15.2 Application of linear neural network15.3 Application of BP neural network15.4 Application of RBF neural network15.5 Summary of this chapterChapter 16 Comprehensive application of neural network16.1 Application of BP neural network16.1.1 Data fitting16.1.2 Data prediction16.1.3 Function approximation16.2 PID neural network control16.3 Genetic algorithm optimization of neural network16.4 Fuzzy neural network control16.5 Probabilistic neural network classification prediction16.6 Chapter Summary Appendix References2 Application of simulated annealing algorithm to combinatorial optimization problem14.2.3 Parameter control of annealing algorithm14.3 Boltzmann machine14.3.1 Network structure of Boltzmann machine14.3.2 Working principle of Boltzmann machine14.3.3 Operation steps of Boltzmann machine14.3.4 Learning rule of Boltzmann machine14.3.5 Improvement of Boltzmann machine14.4 Application of random neural network14.5 Summary of this chapterChapter 15 Basic application of neural network15.1 Application of perceptron neural network15.2 Application of linear neural network15.3 Application of BP neural network15.4 Application of RBF neural network15.5 Summary of this chapterChapter 16 Comprehensive application of neural network16.1 Application of BP neural network16.1.1 Data fitting16.1.2 Data prediction16.1.3 Function approximation16.2 PID neural network control16.3 Genetic algorithm optimization of neural network16.4 Fuzzy neural network control16.5 Probabilistic neural network classification prediction16.6 Chapter Summary Appendix References
You Might Like
Recommended ContentMore
Open source project More
Popular Components
Searched by Users
Just Take a LookMore
Trending Downloads
Trending ArticlesMore