org.neuroph.nnet.learning
Class BinaryDeltaRule
- java.lang.Object
-
- All Implemented Interfaces:
- java.io.Serializable
public class BinaryDeltaRule extends PerceptronLearning
Delta rule learning algorithm for perceptrons with step functions. The difference to Perceptronlearning is that Delta Rule calculates error before the non-lnear step transfer function- See Also:
- Serialized Form
-
-
Constructor Summary
Constructors Constructor and Description BinaryDeltaRule()Creates new BinaryDeltaRule learning
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method and Description doublegetErrorCorrection()Gets the errorCorrection parametarvoidsetErrorCorrection(double errorCorrection)Sets the errorCorrection parametar-
Methods inherited from class org.neuroph.nnet.learning.PerceptronLearning
calculateWeightChanges
-
Methods inherited from class org.neuroph.core.learning.SupervisedLearning
doLearningEpoch, getErrorFunction, getMaxError, getMinErrorChange, getMinErrorChangeIterationsCount, getMinErrorChangeIterationsLimit, getPreviousEpochError, getTotalNetworkError, isBatchMode, learn, learn, setBatchMode, setErrorFunction, setMaxError, setMinErrorChange, setMinErrorChangeIterationsLimit
-
Methods inherited from class org.neuroph.core.learning.IterativeLearning
doOneLearningIteration, getCurrentIteration, getLearningRate, getMaxIterations, isIterationsLimited, isPausedLearning, learn, learn, pause, resume, setLearningRate, setMaxIterations
-
Methods inherited from class org.neuroph.core.learning.LearningRule
addListener, getNeuralNetwork, getTrainingSet, isStopped, removeListener, setNeuralNetwork, setTrainingSet, stopLearning
-
-
-
-
Method Detail
-
getErrorCorrection
public double getErrorCorrection()
Gets the errorCorrection parametar- Returns:
- errorCorrection parametar
-
setErrorCorrection
public void setErrorCorrection(double errorCorrection)
Sets the errorCorrection parametar- Parameters:
errorCorrection- the value for errorCorrection parametar
-
-
DMelt 3.0 © DataMelt by jWork.ORG