Select Index

Getting Started

        Neural Networks
        Basic Chapters
        Mathematical Notation for Equations and Figures
            Basic Concepts
            Weight Matrices
            Layer Notation
            Figure and Equation Examples

        Mathematics and Code Equivalents
        Neural Network Design Book

        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
            Credit Card Activity Checking
            Oil and Gas

    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

            Figures and Equations

            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

            Figures and Equations
            New Functions

    Linear Filters
        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

            Figures and Equations
            New Functions


        Simulation (sim)

    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

    Improving Generalization
        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

Control Systems

    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


Radial Basis Networks

        Important Radial Basis Functions

    Radial Basis Functions
        Neuron Model
        Network Architecture
        Exact Design (newrbe)
        More Efficient Design (newrb)

    Generalized Regression Networks
        Network Architecture
        Design (newgrnn)

    Probabilistic Neural Networks
        Network Architecture
        Design (newpnn)

        New Functions

Self-Organizing and Learn. Vector Quant. Nets

        Important Self-Organizing and LVQ Functions

    Competitive Learning
        Creating a Competitive Neural Network (newc)
        Kohonen Learning Rule (learnk)
        Bias Learning Rule (learncon)
        Graphical Example

    Self-Organizing Maps
        Topologies (gridtop, hextop, randtop)
        Distance Funct. (dist, linkdist, mandist, boxdist)
        Creating a Self Organizing MAP Neural Network (newsom)
        Training (learnsom)

    Learning Vector Quantization Networks
        Creating an LVQ Network (newlvq)
        LVQ1 Learning Rule (learnlv1)
        Supplemental LVQ2.1 Learning Rule (learnlv2)

        Self-Organizing Maps
        Learning Vector Quantizaton Networks
        New Functions

Recurrent Networks

        Important Recurrent Network Functions

    Elman Networks
        Creating an Elman Network (newelm)
        Training an Elman Network

    Hopfield Network
        Design (newhop)

        New Functions

Adaptive Filters and Adaptive Training

        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

        Figures and Equations
        New Functions


        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

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
        Subobject Structures
        Weight and Bias Values

    Subobject Properties
        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



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


    Block Set
        Transfer Function Blocks
        Net Input Blocks
        Weight Blocks

    Block Generation

Code Notes

        Utility Function Variables

    Code Efficiency
    Argument Checking

Printable Documentation (PDF)

Product Page (Web)