org.encog.neural.networks.training.propagation
public class GradientWorker extends Object implements EngineTask
Constructor and Description |
---|
GradientWorker(FlatNetwork theNetwork,
Propagation theOwner,
MLDataSet theTraining,
int theLow,
int theHigh,
double[] flatSpot,
ErrorFunction ef)
Construct a gradient worker.
|
Modifier and Type | Method and Description |
---|---|
ErrorCalculation |
getErrorCalculation() |
FlatNetwork |
getNetwork() |
double[] |
getWeights() |
void |
run()
Perform the gradient calculation for the specified index range.
|
void |
run(int index) |
public GradientWorker(FlatNetwork theNetwork, Propagation theOwner, MLDataSet theTraining, int theLow, int theHigh, double[] flatSpot, ErrorFunction ef)
theNetwork
- The network to train.theOwner
- The owner that is doing the training.theTraining
- The training data.theLow
- The low index to use in the training data.theHigh
- The high index to use in the training data.public FlatNetwork getNetwork()
public double[] getWeights()
public final void run()
run
in interface EngineTask
public final void run(int index)
public ErrorCalculation getErrorCalculation()
Copyright © 2014. All Rights Reserved.