org.neuroph.nnet.learning

Class ManhattanPropagation

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.ManhattanPropagation

All Implemented Interfaces:

Serializable

public class ManhattanPropagation
extends BackPropagation

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
ManhattanPropagation()

Method Summary

Modifier and Type	Method and Description
void	calculateWeightChanges(Neuron neuron) This method calculates weights changes for the single neuron.

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

calculateErrorAndUpdateHiddenNeurons, 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, 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

ManhattanPropagation

public ManhattanPropagation()

Method Detail

calculateWeightChanges

public void calculateWeightChanges(Neuron neuron)

Description copied from class: LMS

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

Overrides:

calculateWeightChanges in class LMS

Parameters:

neuron - neuron to update weights

See Also:

LMS.calculateWeightChanges(double[])