com.practicalstudies.neural
Interface ErrorFunction

All Known Implementing Classes:

HyperbolicTangentFunction, LogisticFunction

public interface ErrorFunction

Represents the calculation of the error in Neuron output, either relative to an actual value, or based on error in the outputs of Neurons to which the Neuron feeds.

Author:

Michael Wax

Method Summary

double	calculateError(double calculatedValue, double actualValue) Calculate the error in Neuron output relative to an actual value (useful for neurons in an output layer).
double	calculateError(double calculatedValue, java.util.List outputConnections) Calculate the error in Neuron output based on errors observed in the outputs of Neurons which rely on the output of this Neuron.

Method Detail

calculateError

public double calculateError(double calculatedValue,
                             double actualValue)

Calculate the error in Neuron output relative to an actual value (useful for neurons in an output layer).

Parameters:

calculatedValue - the calculated output of the Neuron

actualValue - the expected output of the Neuron

calculateError

public double calculateError(double calculatedValue,
                             java.util.List outputConnections)

Calculate the error in Neuron output based on errors observed in the outputs of Neurons which rely on the output of this Neuron.

Parameters:

calculatedValue - the calculated output of the Neuron

outputConnections - a List of WeightedConnections to Neurons which receive the output of this Neuron