Interface NeuralMethod

  • All Superinterfaces:
    java.io.Serializable
    All Known Implementing Classes:
    LinearUnit, SigmoidUnit

    public interface NeuralMethod
    extends java.io.Serializable
    This is an interface used to create classes that can be used by the neuralnode to perform all it's computations.
    Version:
    $Revision: 1.6 $
    Author:
    Malcolm Ware (mfw4@cs.waikato.ac.nz)
    • Method Detail

      • outputValue

        double outputValue​(NeuralNode node)
        This function calculates what the output value should be.
        Parameters:
        node - The node to calculate the value for.
        Returns:
        The value.
      • errorValue

        double errorValue​(NeuralNode node)
        This function calculates what the error value should be.
        Parameters:
        node - The node to calculate the error for.
        Returns:
        The error.
      • updateWeights

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