Custom Neural Networks

Create Neural Network Object

Create and learn the basic components of a neural network object.

Configure Shallow Neural Network Inputs and Outputs

Learn how to manually configure the network before training using the configure function.

Understanding Shallow Network Data Structures

Learn how the format of input data structures affects the simulation of networks.

Edit Shallow Neural Network Properties

Customize network architecture using its properties and use and train the custom network.

Historical and Alternative Neural Networks

Adaptive Neural Network Filters

Design an adaptive linear system that responds to changes in its environment as it is operating.

Perceptron Neural Networks

Learn the architecture, design, and training of perceptron networks for simple classification problems.

Classification with a Two-Input Perceptron

A two-input hard limit neuron is trained to classify four input vectors into two categories.

Outlier Input Vectors

A 2-input hard limit neuron is trained to classify 5 input vectors into two categories.

Normalized Perceptron Rule

A 2-input hard limit neuron is trained to classify 5 input vectors into two categories.

Linearly Non-separable Vectors

A 2-input hard limit neuron fails to properly classify 5 input vectors because they are linearly non-separable.

Radial Basis Neural Networks

Learn to design and use radial basis networks.

Radial Basis Approximation

This example uses the NEWRB function to create a radial basis network that approximates a function defined by a set of data points.

Radial Basis Underlapping Neurons

A radial basis network is trained to respond to specific inputs with target outputs.

Radial Basis Overlapping Neurons

A radial basis network is trained to respond to specific inputs with target outputs.

GRNN Function Approximation

This example uses functions NEWGRNN and SIM.

PNN Classification

This example uses functions NEWPNN and SIM.

Probabilistic Neural Networks

Use probabilistic neural networks for classification problems.

Generalized Regression Neural Networks

Learn to design a generalized regression neural network (GRNN) for function approximation.

Learning Vector Quantization (LVQ) Neural Networks

Create and train a Learning Vector Quantization (LVQ) Neural Network.

Learning Vector Quantization

An LVQ network is trained to classify input vectors according to given targets.

Linear Neural Networks

Design a linear network that, when presented with a set of given input vectors, produces outputs of corresponding target vectors.

Linear Prediction Design

This example illustrates how to design a linear neuron to predict the next value in a time series given the last five values.

Adaptive Linear Prediction

This example shows how an adaptive linear layer can learn to predict the next value in a signal, given the current and last four values.