org.neuroph.nnet.learning
Class StepDeltaRule
java.lang.Object
java.util.Observable
org.neuroph.core.learning.LearningRule
org.neuroph.core.learning.IterativeLearning
org.neuroph.core.learning.SupervisedLearning
org.neuroph.nnet.learning.LMS
org.neuroph.nnet.learning.StepDeltaRule
- All Implemented Interfaces:
- java.io.Serializable, java.lang.Runnable
public class StepDeltaRule
- extends LMS
The StepDeltaRule class implements Delta rule learning algorithm for
perceptrons with step functions.
- See Also:
- Serialized Form
Field Summary |
private double |
e
The e parametar of this learning algorithm |
private static long |
serialVersionUID
The class fingerprint that is set to indicate serialization
compatibility with a previous version of the class. |
Constructor Summary |
StepDeltaRule(NeuralNetwork neuralNetwork)
Creates new StepDeltaRule learning for the specified neural network |
Method Summary |
java.lang.Double |
getE()
Gets the e parametar |
void |
setE(java.lang.Double e)
Sets the e parametar |
protected void |
updateNetworkWeights(java.util.Vector<java.lang.Double> patternError)
This method implements weight update procedure for the whole network for
this learning rule |
Methods inherited from class java.util.Observable |
addObserver, clearChanged, countObservers, deleteObserver, deleteObservers, hasChanged, notifyObservers, notifyObservers, setChanged |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
serialVersionUID
private static final long serialVersionUID
- The class fingerprint that is set to indicate serialization
compatibility with a previous version of the class.
- See Also:
- Constant Field Values
e
private double e
- The e parametar of this learning algorithm
StepDeltaRule
public StepDeltaRule(NeuralNetwork neuralNetwork)
- Creates new StepDeltaRule learning for the specified neural network
- Parameters:
neuralNetwork
-
updateNetworkWeights
protected void updateNetworkWeights(java.util.Vector<java.lang.Double> patternError)
- This method implements weight update procedure for the whole network for
this learning rule
- Overrides:
updateNetworkWeights
in class LMS
- Parameters:
patternError
- single pattern error vector
getE
public java.lang.Double getE()
- Gets the e parametar
- Returns:
- e parametar
setE
public void setE(java.lang.Double e)
- Sets the e parametar
- Parameters:
e
- the value for e parametar