public class ConvolutionalBackpropagation extends MomentumBackpropagation
MomentumBackpropagation.MomentumTrainingData
momentum
maxError, previousEpochError
currentIteration, learningRate, stopConditions
listeners, neuralNetwork, trainingSet
Constructor and Description |
---|
ConvolutionalBackpropagation() |
Modifier and Type | Method and Description |
---|---|
protected void |
calculateErrorAndUpdateHiddenNeurons()
This method implements weights adjustment for the hidden layers
|
protected double |
calculateHiddenNeuronError(Neuron neuron)
Calculates and returns the neuron's error (neuron's delta) for the given neuron param
|
getMomentum, onStart, setMomentum, updateNeuronWeights
calculateErrorAndUpdateOutputNeurons, calculateWeightChanges
afterEpoch, beforeEpoch, doBatchWeightsUpdate, doLearningEpoch, getErrorFunction, getMaxError, getMinErrorChange, getMinErrorChangeIterationsCount, getMinErrorChangeIterationsLimit, getPreviousEpochError, getTotalNetworkError, isBatchMode, learn, learn, learnPattern, setBatchMode, setErrorFunction, setMaxError, setMinErrorChange, setMinErrorChangeIterationsLimit
doOneLearningIteration, getCurrentIteration, getLearningRate, getMaxIterations, hasReachedStopCondition, isIterationsLimited, isPausedLearning, learn, learn, pause, resume, setLearningRate, setMaxIterations
addListener, fireLearningEvent, getNeuralNetwork, getTrainingSet, isStopped, onStop, removeListener, setNeuralNetwork, setTrainingSet, stopLearning
protected void calculateErrorAndUpdateHiddenNeurons()
BackPropagation
calculateErrorAndUpdateHiddenNeurons
in class BackPropagation
protected double calculateHiddenNeuronError(Neuron neuron)
BackPropagation
calculateHiddenNeuronError
in class BackPropagation
neuron
- neuron to calculate error forCopyright © 2017 Neuroph Project. All rights reserved.