org.encog.neural.pattern
Class JordanPattern

java.lang.Object
  org.encog.neural.pattern.JordanPattern

All Implemented Interfaces:

NeuralNetworkPattern

public class JordanPattern
extends Object
implements NeuralNetworkPattern

This class is used to generate an Jordan style recurrent neural network. This network type consists of three regular layers, an input output and hidden layer. There is also a context layer which accepts output from the output layer and outputs back to the hidden layer. This makes it a recurrent neural network. The Jordan neural network is useful for temporal input data. The specified activation function will be used on all layers. The Jordan neural network is similar to the Elman neural network.

Author:

jheaton

Constructor Summary

JordanPattern()
Construct an object to create a Jordan type neural network.

Method Summary

void	addHiddenLayer(int count) Add a hidden layer, there should be only one.
void	clear() Clear out any hidden neurons.
MLMethod	generate() Generate a Jordan neural network.
void	setActivationFunction(ActivationFunction activation) Set the activation function to use on each of the layers.
void	setInputNeurons(int count) Set the number of input neurons.
void	setOutputNeurons(int count) Set the number of output neurons.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

JordanPattern

public JordanPattern()

Construct an object to create a Jordan type neural network.

Method Detail

addHiddenLayer

public final void addHiddenLayer(int count)

Add a hidden layer, there should be only one.

Specified by:

addHiddenLayer in interface NeuralNetworkPattern

Parameters:

count - The number of neurons in this hidden layer.

clear

public final void clear()

Clear out any hidden neurons.

Specified by:

clear in interface NeuralNetworkPattern

generate

public final MLMethod generate()

Generate a Jordan neural network.

Specified by:

generate in interface NeuralNetworkPattern

Returns:

A Jordan neural network.

setActivationFunction

public final void setActivationFunction(ActivationFunction activation)

Set the activation function to use on each of the layers.

Specified by:

setActivationFunction in interface NeuralNetworkPattern

Parameters:

activation - The activation function.

setInputNeurons

public final void setInputNeurons(int count)

Set the number of input neurons.

Specified by:

setInputNeurons in interface NeuralNetworkPattern

Parameters:

count - Neuron count.

setOutputNeurons

public final void setOutputNeurons(int count)

Set the number of output neurons.

Specified by:

setOutputNeurons in interface NeuralNetworkPattern

Parameters:

count - Neuron count.