org.neuroph.nnet.learning

Class LMS

java.lang.Object

org.neuroph.core.learning.LearningRule

org.neuroph.core.learning.IterativeLearning

org.neuroph.core.learning.SupervisedLearning

org.neuroph.nnet.learning.LMS

All Implemented Interfaces:

Serializable

Direct Known Subclasses:

BackPropagation, PerceptronLearning, RBFLearning, SigmoidDeltaRule, SupervisedHebbianLearning

public class LMS
extends SupervisedLearning
implements Serializable

LMS learning rule for neural networks. This learning rule is used to train Adaline neural network, and this class is base for all LMS based learning rules like PerceptronLearning, DeltaRule, SigmoidDeltaRule, Backpropagation etc.

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
LMS() Creates a new LMS learning rule

Method Summary

Modifier and Type	Method and Description
protected void	calculateWeightChanges(double[] outputError) This method implements the weights update procedure for the whole network for the given output error vector.
void	updateNeuronWeights(Neuron neuron) This method implements weights update procedure for the single neuron It iterates through all neuron's input connections, and calculates/set weight change for each weight using formula deltaWeight = learningRate * neuronError * input where neuronError is difference between desired and actual output for specific neuron neuronError = desiredOutput[i] - actualOutput[i] (see method SuprevisedLearning.calculateOutputError)

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

LMS

public LMS()

Creates a new LMS learning rule

Method Detail

calculateWeightChanges

protected void calculateWeightChanges(double[] outputError)

This method implements the weights update procedure for the whole network for the given output error vector.

Specified by:

calculateWeightChanges in class SupervisedLearning

Parameters:

outputError - output error vector for some network input- the difference between desired and actual output

See Also:

learnPattern

updateNeuronWeights

public void updateNeuronWeights(Neuron neuron)

This method implements weights update procedure for the single neuron It iterates through all neuron's input connections, and calculates/set weight change for each weight using formula deltaWeight = learningRate * neuronError * input where neuronError is difference between desired and actual output for specific neuron neuronError = desiredOutput[i] - actualOutput[i] (see method SuprevisedLearning.calculateOutputError)

Parameters:

neuron - neuron to update weights

See Also:

calculateWeightChanges(double[])