Class SigmoidUnit

java.lang.Object
weka.classifiers.functions.neural.SigmoidUnit
All Implemented Interfaces:
Serializable, NeuralMethod, RevisionHandler

public class SigmoidUnit extends Object implements NeuralMethod, RevisionHandler
This can be used by the neuralnode to perform all it's computations (as a sigmoid unit).
Version:
$Revision: 8034 $
Author:
Malcolm Ware (mfw4@cs.waikato.ac.nz)
See Also:
  • Constructor Details

    • SigmoidUnit

      public SigmoidUnit()
  • Method Details

    • outputValue

      public double outputValue(NeuralNode node)
      This function calculates what the output value should be.
      Specified by:
      outputValue in interface NeuralMethod
      Parameters:
      node - The node to calculate the value for.
      Returns:
      The value.
    • errorValue

      public double errorValue(NeuralNode node)
      This function calculates what the error value should be.
      Specified by:
      errorValue in interface NeuralMethod
      Parameters:
      node - The node to calculate the error for.
      Returns:
      The error.
    • updateWeights

      public void updateWeights(NeuralNode node, double learn, double momentum)
      This function will calculate what the change in weights should be and also update them.
      Specified by:
      updateWeights in interface NeuralMethod
      Parameters:
      node - The node to update the weights for.
      learn - The learning rate to use.
      momentum - The momentum to use.
    • getRevision

      public String getRevision()
      Returns the revision string.
      Specified by:
      getRevision in interface RevisionHandler
      Returns:
      the revision