Class SigmoidUnit

  • All Implemented Interfaces:
    java.io.Serializable, NeuralMethod, RevisionHandler

    public class SigmoidUnit
    extends java.lang.Object
    implements NeuralMethod, RevisionHandler
    This can be used by the neuralnode to perform all it's computations (as a sigmoid unit).
    Version:
    $Revision: 1.7 $
    Author:
    Malcolm Ware (mfw4@cs.waikato.ac.nz)
    See Also:
    Serialized Form
    • Constructor Summary

      Constructors 
      Constructor Description
      SigmoidUnit()  
    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method Description
      double errorValue​(NeuralNode node)
      This function calculates what the error value should be.
      java.lang.String getRevision()
      Returns the revision string.
      double outputValue​(NeuralNode node)
      This function calculates what the output value should be.
      void updateWeights​(NeuralNode node, double learn, double momentum)
      This function will calculate what the change in weights should be and also update them.
      • Methods inherited from class java.lang.Object

        equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • SigmoidUnit

        public SigmoidUnit()
    • Method Detail

      • 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 java.lang.String getRevision()
        Returns the revision string.
        Specified by:
        getRevision in interface RevisionHandler
        Returns:
        the revision