org.neuroph.nnet.learning

Class DynamicBackPropagation

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

org.neuroph.nnet.learning.DynamicBackPropagation

All Implemented Interfaces:

Serializable

public class DynamicBackPropagation
extends MomentumBackpropagation

Backpropagation learning rule with dynamic learning rate and momentum

Author:

Zoran Sevarac

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.neuroph.nnet.learning.MomentumBackpropagation

MomentumBackpropagation.MomentumTrainingData

Field Summary

Fields inherited from class org.neuroph.nnet.learning.MomentumBackpropagation

momentum

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
DynamicBackPropagation()

Method Summary

Modifier and Type	Method and Description
protected void	adjustLearningRate()
protected void	adjustMomentum()
void	doLearningEpoch(DataSet trainingSet) This method implements basic logic for one learning epoch for the supervised learning algorithms.
double	getLearningRateChange()
double	getMaxLearningRate()
double	getMaxMomentum()
double	getMinLearningRate()
double	getMinMomentum()
double	getMomentumChange()
boolean	getUseDynamicLearningRate()
boolean	getUseDynamicMomentum()
void	setLearningRateChange(double learningRateChange)
void	setMaxLearningRate(double maxLearningRate)
void	setMaxMomentum(double maxMomentum)
void	setMinLearningRate(double minLearningRate)
void	setMinMomentum(double minMomentum)
void	setMomentumChange(double momentumChange)
void	setUseDynamicLearningRate(boolean useDynamicLearningRate)
void	setUseDynamicMomentum(boolean useDynamicMomentum)

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

calculateErrorAndUpdateHiddenNeurons, calculateWeightChanges, getMomentum, onStart, setMomentum

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

calculateErrorAndUpdateOutputNeurons, calculateHiddenNeuronError, calculateWeightChanges

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

afterEpoch, beforeEpoch, doBatchWeightsUpdate, 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

Constructor Detail

DynamicBackPropagation

public DynamicBackPropagation()

Method Detail

adjustLearningRate

protected void adjustLearningRate()

adjustMomentum

protected void adjustMomentum()

doLearningEpoch

public void doLearningEpoch(DataSet trainingSet)

Description copied from class: SupervisedLearning

This method implements basic logic for one learning epoch for the supervised learning algorithms. Epoch is the one pass through the training set. This method iterates through the training set and trains network for each element. It also sets flag if conditions to stop learning has been reached: network error below some allowed value, or maximum iteration count

Overrides:

doLearningEpoch in class SupervisedLearning

Parameters:

trainingSet - training set for training network

getLearningRateChange

public double getLearningRateChange()

setLearningRateChange

public void setLearningRateChange(double learningRateChange)

getMaxLearningRate

public double getMaxLearningRate()

setMaxLearningRate

public void setMaxLearningRate(double maxLearningRate)

getMaxMomentum

public double getMaxMomentum()

setMaxMomentum

public void setMaxMomentum(double maxMomentum)

getMinLearningRate

public double getMinLearningRate()

setMinLearningRate

public void setMinLearningRate(double minLearningRate)

getMinMomentum

public double getMinMomentum()

setMinMomentum

public void setMinMomentum(double minMomentum)

getMomentumChange

public double getMomentumChange()

setMomentumChange

public void setMomentumChange(double momentumChange)

getUseDynamicLearningRate

public boolean getUseDynamicLearningRate()

setUseDynamicLearningRate

public void setUseDynamicLearningRate(boolean useDynamicLearningRate)

getUseDynamicMomentum

public boolean getUseDynamicMomentum()

setUseDynamicMomentum

public void setUseDynamicMomentum(boolean useDynamicMomentum)