org.encog.engine.network.train.gradient
Class GradientWorkerCPU

java.lang.Object
  org.encog.engine.network.train.gradient.GradientWorkerCPU

All Implemented Interfaces:

EngineTask, FlatGradientWorker

public class GradientWorkerCPU
extends Object
implements FlatGradientWorker

Worker class for the mulithreaded training of flat networks.

Constructor Summary

GradientWorkerCPU(FlatNetwork network, TrainFlatNetworkProp owner, EngineIndexableSet training, int low, int high)
Construct a gradient worker.

Method Summary

long	getElapsedTime()
FlatNetwork	getNetwork()
double[]	getWeights()
void	run() Perform the gradient calculation for the specified index range.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

GradientWorkerCPU

public GradientWorkerCPU(FlatNetwork network,
                         TrainFlatNetworkProp owner,
                         EngineIndexableSet training,
                         int low,
                         int high)

Construct a gradient worker.

Parameters:

network - The network to train.

owner - The owner that is doing the training.

training - The training data.

low - The low index to use in the training data.

high - The high index to use in the training data.

Method Detail

getElapsedTime

public long getElapsedTime()

Specified by:

getElapsedTime in interface FlatGradientWorker

Returns:

Elapsed time for the last iteration.

getNetwork

public FlatNetwork getNetwork()

Specified by:

getNetwork in interface FlatGradientWorker

Returns:

The network training.

getWeights

public double[] getWeights()

Specified by:

getWeights in interface FlatGradientWorker

Returns:

The weights for this network.

run

public void run()

Perform the gradient calculation for the specified index range.

Specified by:

run in interface EngineTask