org.neuroph.nnet.learning

Class MomentumBackpropagation

java.lang.Object

org.neuroph.core.learning.LearningRule

org.neuroph.core.learning.IterativeLearning

org.neuroph.core.learning.SupervisedLearning

org.neuroph.nnet.learning.LMS

org.neuroph.nnet.learning.BackPropagation

org.neuroph.nnet.learning.MomentumBackpropagation

All Implemented Interfaces:

Serializable

Direct Known Subclasses:

ConvolutionalBackpropagation, DynamicBackPropagation

public class MomentumBackpropagation
extends BackPropagation

Backpropagation learning rule with momentum.

Author:

Zoran Sevarac

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	MomentumBackpropagation.MomentumTrainingData

Field Summary

Fields

Modifier and Type	Field and Description
protected double	momentum Momentum factor

Fields inherited from class org.neuroph.core.learning.SupervisedLearning

maxError, previousEpochError

Fields inherited from class org.neuroph.core.learning.IterativeLearning

currentIteration, learningRate, stopConditions

Fields inherited from class org.neuroph.core.learning.LearningRule

listeners, neuralNetwork, trainingSet

Constructor Summary

Constructors

Constructor and Description
MomentumBackpropagation() Creates new instance of MomentumBackpropagation learning

Method Summary

Modifier and Type	Method and Description
protected void	calculateErrorAndUpdateHiddenNeurons() This method implements weights adjustment for the hidden layers Uses parallel processing on each layer with 100 or more neurons and a regular loop if less.
void	calculateWeightChanges(Neuron neuron) This method implements weights update procedure for the single neuron for the back propagation with momentum factor
double	getMomentum() Returns the momentum factor
protected void	onStart() This method is executed when learning starts, before the first epoch.
void	setMomentum(double momentum) Sets the momentum factor

Methods inherited from class org.neuroph.nnet.learning.BackPropagation

calculateErrorAndUpdateOutputNeurons, calculateHiddenNeuronError, calculateWeightChanges

Methods inherited from class org.neuroph.core.learning.SupervisedLearning

afterEpoch, beforeEpoch, doBatchWeightsUpdate, doLearningEpoch, getErrorFunction, getMaxError, getMinErrorChange, getMinErrorChangeIterationsCount, getMinErrorChangeIterationsLimit, getPreviousEpochError, getTotalNetworkError, isBatchMode, learn, learn, learnPattern, setBatchMode, setErrorFunction, setMaxError, setMinErrorChange, setMinErrorChangeIterationsLimit

Methods inherited from class org.neuroph.core.learning.IterativeLearning

doOneLearningIteration, getCurrentIteration, getLearningRate, getMaxIterations, hasReachedStopCondition, isIterationsLimited, isPausedLearning, learn, learn, pause, resume, setLearningRate, setMaxIterations

Methods inherited from class org.neuroph.core.learning.LearningRule

addListener, fireLearningEvent, getNeuralNetwork, getTrainingSet, isStopped, onStop, removeListener, setNeuralNetwork, setTrainingSet, stopLearning

Methods inherited from class java.lang.Object

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

Field Detail

momentum

protected double momentum

Momentum factor

Constructor Detail

MomentumBackpropagation

public MomentumBackpropagation()

Creates new instance of MomentumBackpropagation learning

Method Detail

calculateErrorAndUpdateHiddenNeurons

protected void calculateErrorAndUpdateHiddenNeurons()

This method implements weights adjustment for the hidden layers Uses parallel processing on each layer with 100 or more neurons and a regular loop if less.

Overrides:

calculateErrorAndUpdateHiddenNeurons in class BackPropagation

calculateWeightChanges

public void calculateWeightChanges(Neuron neuron)

This method implements weights update procedure for the single neuron for the back propagation with momentum factor

Overrides:

calculateWeightChanges in class LMS

Parameters:

neuron - neuron to update weights

See Also:

LMS.calculateWeightChanges(double[])

getMomentum

public double getMomentum()

Returns the momentum factor

Returns:

momentum factor

setMomentum

public void setMomentum(double momentum)

Sets the momentum factor

Parameters:

momentum - momentum factor

onStart

protected void onStart()

Description copied from class: IterativeLearning

This method is executed when learning starts, before the first epoch. Used for initialisation.

Overrides:

onStart in class SupervisedLearning