org.encog.neural.networks.training.propagation
Class GradientWorker

java.lang.Object
  extended by org.encog.neural.networks.training.propagation.GradientWorker
All Implemented Interfaces:
EngineTask

public class GradientWorker
extends Object
implements EngineTask

Worker class for the mulithreaded training of flat networks.


Constructor Summary
GradientWorker(FlatNetwork theNetwork, Propagation theOwner, MLDataSet theTraining, int theLow, int theHigh, double[] flatSpot, ErrorFunction ef)
          Construct a gradient worker.
 
Method Summary
 ErrorCalculation getErrorCalculation()
           
 FlatNetwork getNetwork()
           
 double[] getWeights()
           
 void run()
          Perform the gradient calculation for the specified index range.
 void run(int index)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

GradientWorker

public GradientWorker(FlatNetwork theNetwork,
                      Propagation theOwner,
                      MLDataSet theTraining,
                      int theLow,
                      int theHigh,
                      double[] flatSpot,
                      ErrorFunction ef)
Construct a gradient worker.

Parameters:
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.
Method Detail

getNetwork

public FlatNetwork getNetwork()
Returns:
The network being processed.

getWeights

public double[] getWeights()
Returns:
The weights for this network.

run

public final void run()
Perform the gradient calculation for the specified index range.

Specified by:
run in interface EngineTask

run

public final void run(int index)

getErrorCalculation

public ErrorCalculation getErrorCalculation()


Copyright © 2014. All Rights Reserved.