All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home

Interface weka.classifiers.neural.NeuralMethod

public interface NeuralMethod
extends Serializable
This is an interface used to create classes that can be used by the neuralnode to perform all it's computations.

Author:
Malcolm Ware (mfw4@cs.waikato.ac.nz)

Method Index

 o errorValue(NeuralNode)
This function calculates what the error value should be.
 o outputValue(NeuralNode)
This function calculates what the output value should be.
 o updateWeights(NeuralNode, double, double)
This function will calculate what the change in weights should be and also update them.

Methods

 o outputValue
 public abstract 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.
 o errorValue
 public abstract 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.
 o updateWeights
 public abstract 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.

All Packages  Class Hierarchy  This Package  Previous  Next  Index  WEKA's home