Interface NeuralMethod
- All Superinterfaces:
Serializable
- All Known Implementing Classes:
LinearUnit,SigmoidUnit
This is an interface used to create classes that can be used by the
neuralnode to perform all it's computations.
- Version:
- $Revision: 8034 $
- Author:
- Malcolm Ware (mfw4@cs.waikato.ac.nz)
-
Method Summary
Modifier and TypeMethodDescriptiondoubleerrorValue(NeuralNode node) This function calculates what the error value should be.doubleoutputValue(NeuralNode node) This function calculates what the output value should be.voidupdateWeights(NeuralNode node, double learn, double momentum) This function will calculate what the change in weights should be and also update them.
-
Method Details
-
outputValue
This function calculates what the output value should be.- Parameters:
node- The node to calculate the value for.- Returns:
- The value.
-
errorValue
This function calculates what the error value should be.- Parameters:
node- The node to calculate the error for.- Returns:
- The error.
-
updateWeights
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.
-