org.neuroph.nnet.learning

Class BackPropagation

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

All Implemented Interfaces:

Serializable

Direct Known Subclasses:

ManhattanPropagation, MomentumBackpropagation, QuickPropagation, ResilientPropagation

public class BackPropagation
extends LMS

Back Propagation learning rule for Multi Layer Perceptron neural networks.

Author:

Zoran Sevarac

See Also:

Serialized Form

Field Summary

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
BackPropagation() Creates new instance of BackPropagation learning

Method Summary

Modifier and Type	Method and Description
protected void	calculateErrorAndUpdateHiddenNeurons() This method implements weights adjustment for the hidden layers
protected void	calculateErrorAndUpdateOutputNeurons(double[] outputError) This method implements weights update procedure for the output neurons Calculates delta/error and calls updateNeuronWeights to update neuron's weights for each output neuron
protected double	calculateHiddenNeuronError(Neuron neuron) Calculates and returns the neuron's error (neuron's delta) for the given neuron param
protected void	calculateWeightChanges(double[] outputError) This method implements weight update procedure for the whole network for the specified output error vector.

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

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, onStart, 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

BackPropagation

public BackPropagation()

Creates new instance of BackPropagation learning

Method Detail

calculateWeightChanges

protected void calculateWeightChanges(double[] outputError)

This method implements weight update procedure for the whole network for the specified output error vector.

Overrides:

calculateWeightChanges in class LMS

Parameters:

outputError - output error vector

See Also:

learnPattern

calculateErrorAndUpdateOutputNeurons

protected void calculateErrorAndUpdateOutputNeurons(double[] outputError)

This method implements weights update procedure for the output neurons Calculates delta/error and calls updateNeuronWeights to update neuron's weights for each output neuron

Parameters:

outputError - error vector for output neurons

calculateErrorAndUpdateHiddenNeurons

protected void calculateErrorAndUpdateHiddenNeurons()

This method implements weights adjustment for the hidden layers

calculateHiddenNeuronError

protected double calculateHiddenNeuronError(Neuron neuron)

Calculates and returns the neuron's error (neuron's delta) for the given neuron param

Parameters:

neuron - neuron to calculate error for

Returns:

neuron error (delta) for the specified neuron