boone.training

Class HopfieldDeltaTrainer

java.lang.Object

boone.Trainer

boone.training.HopfieldDeltaTrainer

All Implemented Interfaces:

Storable, java.lang.Cloneable

public class HopfieldDeltaTrainer
extends Trainer

Trainer for Hopfield networks using the delta learning rule.

Version:

$Id$

Author:

August Mayer, Helmut A. Mayer

Field Summary

Fields inherited from class boone.Trainer

currentEpoch, epochs, learnRate, net, shuffle, stepMode, testData, trainingData, trainingSignalGenerator

Constructor Summary

Constructors

Constructor and Description
HopfieldDeltaTrainer()

Method Summary

Modifier and Type	Method and Description
protected double	calcAdaptation(BrainPart part) Calculates the adaptation value based on the gradient.
protected void	endBatch() Does nothing.
protected void	endTrain() Does nothing.
void	fromXML(org.jdom2.Element element) Reads attributes from XML.
protected void	reset() Does nothing.
void	train(java.util.List<java.lang.Double> input, java.util.List<java.lang.Double> target) Performs training of the Hopfield network.

Methods inherited from class boone.Trainer

clone, getBatchSize, getEpochs, getLearnRate, getNetwork, getRank, getTestData, getTrainingData, getTrainingSignalGenerator, getWinningNeuron, setBatchSize, setEpochs, setLearnRate, setNetwork, setShuffle, setStepMode, setTestData, setTrainingData, setTrainingSignalGenerator, test, test, toString, toXML, train, trainPattern, updateLinks, updateNeurons

Methods inherited from class java.lang.Object

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

Constructor Detail

HopfieldDeltaTrainer

public HopfieldDeltaTrainer()

Method Detail

reset

protected void reset()

Does nothing.

Specified by:

reset in class Trainer

endBatch

protected void endBatch()

Does nothing.

Overrides:

endBatch in class Trainer

endTrain

protected void endTrain()

Does nothing.

Specified by:

endTrain in class Trainer

calcAdaptation

protected double calcAdaptation(BrainPart part)

Calculates the adaptation value based on the gradient.

Specified by:

calcAdaptation in class Trainer

Parameters:

part - the brain part to be adapted

Returns:

the adaptation value is 0!

train

public void train(java.util.List<java.lang.Double> input,
                  java.util.List<java.lang.Double> target)

Performs training of the Hopfield network. First innervates the network and then trains a single neuron selected at random using the delta rule. For training of this neuron (weights and biases) of all other neurons are assigned the correct output values for a pattern, so the neuron being trained is adapting to the correct values of a pattern.

Specified by:

train in class Trainer

Parameters:

input - an input pattern

target - a target pattern

fromXML

public void fromXML(org.jdom2.Element element)

Description copied from class: Trainer

Reads attributes from XML.

Specified by:

fromXML in interface Storable

Overrides:

fromXML in class Trainer

Parameters:

element - a JDOM element