org.neuroph.core.learning.error

Interface ErrorFunction

All Known Implementing Classes:

MeanAbsoluteError, MeanSquaredError

public interface ErrorFunction

Interface for calculating total network error during the learning. Custom error types can be implemented.

Author:

Zoran Sevarac

Method Summary

Modifier and Type	Method and Description
double[]	addPatternError(double[] predictedOutput, double[] targetOutput) Calculates and adds pattern error for the given predicted and target output vector and adds it to total error.
double	getTotalError() Return total network error
void	reset() Sets total error and pattern count to zero.

Method Detail

getTotalError

double getTotalError()

Return total network error

Returns:

total network error

addPatternError

double[] addPatternError(double[] predictedOutput,
                         double[] targetOutput)

Calculates and adds pattern error for the given predicted and target output vector and adds it to total error.

Parameters:

predictedOutput - actual network output

targetOutput - target/desired output

Returns:

returns pattern error vector

reset

void reset()

Sets total error and pattern count to zero.