org.encog.neural.networks.training.concurrent.jobs
Class RPROPJob

java.lang.Object
  org.encog.neural.networks.training.concurrent.jobs.TrainingJob
      org.encog.neural.networks.training.concurrent.jobs.RPROPJob

public class RPROPJob
extends TrainingJob

A training definition for RPROP training.

Constructor Summary

RPROPJob(BasicNetwork network, NeuralDataSet training, boolean loadToMemory)
Construct an RPROP job.

RPROPJob(BasicNetwork network, NeuralDataSet training, boolean loadToMemory, double initialUpdate, double maxStep, double localRatio, int globalRatio, double segmentationRatio, int iterationsPer)
Construct an RPROP job.

RPROPJob(BasicNetwork network, NeuralDataSet training, boolean loadToMemory, double localRatio, int globalRatio, double segmentationRatio, int iterationsPer)
Construct an RPROP job.

Method Summary

void	createTrainer(OpenCLTrainingProfile profile, boolean singleThreaded) Create a trainer to use.
double	getInitialUpdate()
double	getMaxStep()
void	setInitialUpdate(double initialUpdate)
void	setMaxStep(double maxStep)

Methods inherited from class org.encog.neural.networks.training.concurrent.jobs.TrainingJob

getError, getGlobalRatio, getIterationsPer, getLocalRatio, getNetwork, getSegmentationRatio, getStrategies, getTrain, getTraining, isLoadToMemory, setError, setGlobalRatio, setIterationsPer, setLoadToMemory, setLocalRatio, setNetwork, setSegmentationRatio, setTrain, setTraining, shouldContinue

Methods inherited from class java.lang.Object

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

Constructor Detail

RPROPJob

public RPROPJob(BasicNetwork network,
                NeuralDataSet training,
                boolean loadToMemory)

Construct an RPROP job. For more information on RPROP see the ResilientPropagation class.

Parameters:

network - The network to train.

training - The training data to use.

loadToMemory - True if binary training data should be loaded to memory.

RPROPJob

public RPROPJob(BasicNetwork network,
                NeuralDataSet training,
                boolean loadToMemory,
                double localRatio,
                int globalRatio,
                double segmentationRatio,
                int iterationsPer)

Construct an RPROP job. For more information on RPROP see the ResilientPropagation class.

Parameters:

network - The network to train.

training - The training data to use.

loadToMemory - True if binary training data should be loaded to memory.

localRatio - The local ratio, used if this job is performed by an OpenCL Device.

globalRatio - The global ratio, used if this job is performed by an OpenCL Device.

segmentationRatio - The segmentation ratio, used if this job is performed by an OpenCL Device.

iterationsPer - How many iterations to process per cycle.

RPROPJob

public RPROPJob(BasicNetwork network,
                NeuralDataSet training,
                boolean loadToMemory,
                double initialUpdate,
                double maxStep,
                double localRatio,
                int globalRatio,
                double segmentationRatio,
                int iterationsPer)

Construct an RPROP job. For more information on RPROP see the ResilientPropagation class.

Parameters:

network - The network to train.

training - The training data to use.

loadToMemory - True if binary training data should be loaded to memory.

initialUpdate - The initial update.

maxStep - The max step.

localRatio - The local ratio, used if this job is performed by an OpenCL Device.

globalRatio - The global ratio, used if this job is performed by an OpenCL Device.

segmentationRatio - The segmentation ratio, used if this job is performed by an OpenCL Device.

iterationsPer - How many iterations to process per cycle.

Method Detail

createTrainer

public void createTrainer(OpenCLTrainingProfile profile,
                          boolean singleThreaded)

Create a trainer to use.

Specified by:

createTrainer in class TrainingJob

Parameters:

profile - The OpenCL training profile to use.

getInitialUpdate

public double getInitialUpdate()

Returns:

the initialUpdate

getMaxStep

public double getMaxStep()

Returns:

the maxStep

setInitialUpdate

public void setInitialUpdate(double initialUpdate)

Parameters:

initialUpdate - the initialUpdate to set

setMaxStep

public void setMaxStep(double maxStep)

Parameters:

maxStep - the maxStep to set