org.neuroph.nnet.learning

Class CompetitiveLearning

java.lang.Object

org.neuroph.core.learning.LearningRule

org.neuroph.core.learning.IterativeLearning

org.neuroph.core.learning.UnsupervisedLearning

org.neuroph.nnet.learning.CompetitiveLearning

All Implemented Interfaces:

Serializable

public class CompetitiveLearning
extends UnsupervisedLearning

Competitive learning rule.

Author:

Zoran Sevarac

See Also:

Serialized Form

Field Summary

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
CompetitiveLearning() Creates new instance of CompetitiveLearning

Method Summary

Modifier and Type	Method and Description
void	doLearningEpoch(DataSet trainingSet) This method does one learning epoch for the unsupervised learning rules.
protected void	updateNetworkWeights() Adjusts weights for the winning neuron

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

learnPattern

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

afterEpoch, beforeEpoch, doOneLearningIteration, getCurrentIteration, getLearningRate, getMaxIterations, hasReachedStopCondition, isIterationsLimited, isPausedLearning, learn, learn, onStart, 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

CompetitiveLearning

public CompetitiveLearning()

Creates new instance of CompetitiveLearning

Method Detail

doLearningEpoch

public void doLearningEpoch(DataSet trainingSet)

This method does one learning epoch for the unsupervised learning rules. It iterates through the training set and trains network weights for each element. Stops learning after one epoch.

Overrides:

doLearningEpoch in class UnsupervisedLearning

Parameters:

trainingSet - training set for training network

updateNetworkWeights

protected void updateNetworkWeights()

Adjusts weights for the winning neuron

Specified by:

updateNetworkWeights in class UnsupervisedLearning