Neural Network Toolbox Getting Started Preface Neural Networks Basic Chapters Mathematical Notation for Equations and Figures Basic Concepts Language Weight Matrices Layer Notation Figure and Equation Examples Mathematics and Code Equivalents Neural Network Design Book Acknowledgments Introduction Getting Started Basic Chapters Help and Installation What's New in Version 4.0 Control System Applications Graphical User Interface New Training Functions Design of General Linear Networks Improved Early Stopping Generalization and Speed Benchmarks Demonstration of a Sample Training Session Neural Network Applications Applications in this Toolbox Business Applications Aerospace Automotive Banking Credit Card Activity Checking Defense Electronics Entertainment Financial Industrial Insurance Manufacturing Medical Oil and Gas Robotics Speech Securities Telecommunications Transportation Summary Neuron Model and Network Architectures Neuron Model Simple Neuron Transfer Functions Neuron with Vector Input Network Architectures A Layer of Neurons Multiple Layers of Neurons Data Structures Simulation With Concurrent Inputs in a Static Network Simulation With Sequential Inputs in a Dynamic Network Simulation With Concurrent Inputs in a Dynamic Network Training Styles Incremental Training (of Adaptive and Other Networks) Batch Training Summary Figures and Equations Perceptrons Introduction Important Perceptron Functions Neuron Model Perceptron Architecture Creating a Perceptron (newp) Simulation (sim) Initialization (init) Learning Rules Perceptron Learning Rule (learnp) Training (train) Limitations and Cautions Outliers and the Normalized Perceptron Rule Graphical User Interface Introduction to the GUI Create a Perceptron Network (nntool) Train the Perceptron Export Perceptron Results to Workspace Clear Network/Data Window Importing from the Command Line Save a Variable to a File and Load It Later Summary Figures and Equations New Functions Linear Filters Introduction Neuron Model Network Architecture Creating a Linear Neuron (newlin) Mean Square Error Linear System Design (newlind) Linear Networks with Delays Tapped Delay Line Linear Filter LMS Algorithm (learnwh) Linear Classification (train) Limitations and Cautions Overdetermined Systems Underdetermined Systems Linearly Dependent Vectors Too Large a Learning Rate Summary Figures and Equations New Functions Backpropagation Introduction Fundamentals Architecture Simulation (sim) Training Faster Training Variable Learning Rate (traingda, traingdx) Resilient Backpropagation (trainrp) Conjugate Gradient Algorithms Line Search Routines Quasi-Newton Algorithms Levenberg-Marquardt (trainlm) Reduced Memory Levenberg-Marquardt (trainlm) Speed and Memory Comparison Summary Improving Generalization Regularization Early Stopping Summary and Discussion Preprocessing and Postprocessing Min and Max (premnmx, postmnmx, tramnmx) Mean and Stand. Dev. (prestd, poststd, trastd) Principal Component Analysis (prepca, trapca) Post-Training Analysis (postreg) Sample Training Session Limitations and Cautions Summary Control Systems Introduction NN Predictive Control System Identification Predictive Control Using the NN Predictive Controller Block NARMA-L2 (Feedback Linearization) Control Identification of the NARMA-L2 Model NARMA-L2 Controller Using the NARMA-L2 Controller Block Model Reference Control Using the Model Reference Controller Block Importing and Exporting Importing and Exporting Networks Importing and Exporting Training Data Summary Radial Basis Networks Introduction Important Radial Basis Functions Radial Basis Functions Neuron Model Network Architecture Exact Design (newrbe) More Efficient Design (newrb) Demonstrations Generalized Regression Networks Network Architecture Design (newgrnn) Probabilistic Neural Networks Network Architecture Design (newpnn) Summary Figures New Functions Self-Organizing and Learn. Vector Quant. Nets Introduction Important Self-Organizing and LVQ Functions Competitive Learning Architecture Creating a Competitive Neural Network (newc) Kohonen Learning Rule (learnk) Bias Learning Rule (learncon) Training Graphical Example Self-Organizing Maps Topologies (gridtop, hextop, randtop) Distance Funct. (dist, linkdist, mandist, boxdist) Architecture Creating a Self Organizing MAP Neural Network (newsom) Training (learnsom) Examples Learning Vector Quantization Networks Architecture Creating an LVQ Network (newlvq) LVQ1 Learning Rule (learnlv1) Training Supplemental LVQ2.1 Learning Rule (learnlv2) Summary Self-Organizing Maps Learning Vector Quantizaton Networks Figures New Functions Recurrent Networks Introduction Important Recurrent Network Functions Elman Networks Architecture Creating an Elman Network (newelm) Training an Elman Network Hopfield Network Fundamentals Architecture Design (newhop) Summary Figures New Functions Adaptive Filters and Adaptive Training Introduction Important Adaptive Functions Linear Neuron Model Adaptive Linear Network Architecture Single ADALINE (newlin) Mean Square Error LMS Algorithm (learnwh) Adaptive Filtering (adapt) Tapped Delay Line Adaptive Filter Adaptive Filter Example Prediction Example Noise Cancellation Example Multiple Neuron Adaptive Filters Summary Figures and Equations New Functions Applications Introduction Application Scripts Applin1: Linear Design Problem Definition Network Design Network Testing Thoughts and Conclusions Applin2: Adaptive Prediction Problem Definition Network Initialization Network Training Network Testing Thoughts and Conclusions Appelm1: Amplitude Detection Problem Definition Network Initialization Network Training Network Testing Network Generalization Improving Performance Appcr1: Character Recognition Problem Statement Neural Network System Performance Summary Advanced Topics Custom Networks Custom Network Network Definition Network Behavior Additional Toolbox Functions Initialization Functions Transfer Functions Learning Functions Custom Functions Simulation Functions Initialization Functions Learning Functions Self-Organizing Map Functions Network Object Reference Network Properties Architecture Subobject Structures Functions Parameters Weight and Bias Values Other Subobject Properties Inputs Layers Outputs Targets Biases Input Weights Layer Weights Functions -- Categorical List Analysis Functions Distance Functions Graphical Interface Function Layer Initialization Functions Learning Functions Line Search Functions Net Input Derivative Functions Net Input Functions Network Functions Network Initialization Function Network Use Functions New Networks Functions Performance Derivative Functions Performance Functions Plotting Functions Pre- and Postprocessing Functions Simulink Support Function Topology Functions Training Functions Transfer Derivative Functions Transfer Functions Utility Functions Vector Functions Weight and Bias Initialization Functions Weight Derivative Functions Weight Functions Transfer Function Graphs Functions -- Alphabetical List Glossary Bibliography Demonstrations and Applications Tables of Demonstrations and Applications Chapter 2: Neuron Model and Network Architectures Chapter 3: Perceptrons Chapter 4: Linear Filters Chapter 5: Backpropagation Chapter 7: Radial Basis Networks Chapter 8: Self-Organizing and Learn. Vector Quant. Nets Chapter 9: Recurrent Networks Chapter 10: Adaptive Networks Chapter 11: Applications Simulink Block Set Transfer Function Blocks Net Input Blocks Weight Blocks Block Generation Example Exercises Code Notes Dimensions Variables Utility Function Variables Functions Code Efficiency Argument Checking Release Notes Neural Network Toolbox 4.0.1 Release Notes Major Bug Fixes Proper Use of Validation and Test Data Correct Version 3 Object Loading Neural Network Toolbox 4.0 Release Notes New Features Control System Applications Visual Interface New Training Functions Design of General Linear Networks Improved Early Stopping Generalization and Speed Benchmarks Demonstration of a Sample Training Session Upgrading from an Earlier Release Use of trainwb and trainwb1 Not Recommended Printable Documentation (PDF) Product Page (Web)