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

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

public class RPROPJob
extends TrainingJob

A training definition for RPROP training.


Constructor Summary
RPROPJob(BasicNetwork network, MLDataSet training, boolean loadToMemory)
          Construct an RPROP job.
 
Method Summary
 void createTrainer(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, getNetwork, getStrategies, getTrain, getTraining, isLoadToMemory, setError, setLoadToMemory, setNetwork, 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,
                MLDataSet 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.
Method Detail

createTrainer

public void createTrainer(boolean singleThreaded)
Create a trainer to use.

Specified by:
createTrainer in class TrainingJob

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


Copyright © 2014. All Rights Reserved.