org.neuroph.nnet.learning
Class LMS
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
- All Implemented Interfaces:
- java.io.Serializable, java.lang.Runnable
- Direct Known Subclasses:
- SigmoidDeltaRule, StepDeltaRule, SupervisedHebbianLearning
public class LMS
- extends SupervisedLearning
- implements java.io.Serializable
The LMS class implements LMS learning rule for neural networks.
- See Also:
- Serialized Form
Field Summary |
private static long |
serialVersionUID
The class fingerprint that is set to indicate serialization
compatibility with a previous version of the class. |
Constructor Summary |
LMS(NeuralNetwork neuralNetwork)
Creates new LMS learning rule for specified neural network |
Method Summary |
protected void |
updateNetworkWeights(java.util.Vector<java.lang.Double> patternError)
This method implements weight update procedure for the whole network for
this learning rule |
protected void |
updateNeuronWeights(Neuron neuron)
This method implements weights update procedure for the single neuron |
protected void |
updateTotalNetworkError(java.util.Vector<java.lang.Double> patternError)
Updates total network error with specified pattern error vector |
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
LMS
public LMS(NeuralNetwork neuralNetwork)
- Creates new LMS learning rule for specified neural network
- Parameters:
network
-
updateTotalNetworkError
protected void updateTotalNetworkError(java.util.Vector<java.lang.Double> patternError)
- Updates total network error with specified pattern error vector
- Specified by:
updateTotalNetworkError
in class SupervisedLearning
- Parameters:
patternError
- single pattern error vector
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
- Specified by:
updateNetworkWeights
in class SupervisedLearning
- Parameters:
patternError
- single pattern error vector
updateNeuronWeights
protected void updateNeuronWeights(Neuron neuron)
- This method implements weights update procedure for the single neuron
- Parameters:
neuron
- neuron to update weights