org.encog.neural.networks.training.propagation

Interface GradientWorkerOwner

All Known Implementing Classes:

Backpropagation, ManhattanPropagation, Propagation, QuickPropagation, ResilientPropagation, ScaledConjugateGradient

public interface GradientWorkerOwner

Method Summary

Modifier and Type	Method and Description
double	getL1()
double	getL2()
void	report(double[] gradients, double error, java.lang.Throwable ex) Called by the worker threads to report the progress at each step.

Method Detail

report

void report(double[] gradients,
            double error,
            java.lang.Throwable ex)

Called by the worker threads to report the progress at each step.

Parameters:

gradients - The gradients from that worker.

error - The error for that worker.

ex - The exception.

getL1

double getL1()

Returns:

How much to apply l1 regularization penalty, 0 (default) for none.

getL2

double getL2()

Returns:

How much to apply l2 regularization penalty, 0 (default) for none.