org.encog.neural.freeform.training

Class FreeformResilientPropagation

java.lang.Object

org.encog.ml.train.BasicTraining

org.encog.neural.freeform.training.FreeformPropagationTraining

org.encog.neural.freeform.training.FreeformResilientPropagation

All Implemented Interfaces:

Serializable, MLTrain

public class FreeformResilientPropagation
extends FreeformPropagationTraining
implements Serializable

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static int	TEMP_GRADIENT Temp value #0: the gradient.
static int	TEMP_LAST_GRADIENT Temp value #1: the last gradient.
static int	TEMP_LAST_WEIGHT_DELTA Temp value #3: the the last weight delta.
static int	TEMP_UPDATE Temp value #2: the update.

Fields inherited from class org.encog.neural.freeform.training.FreeformPropagationTraining

FLAT_SPOT_CONST

Constructor Summary

Constructors

Constructor and Description
FreeformResilientPropagation(FreeformNetwork theNetwork, MLDataSet theTraining) Construct the RPROP trainer, Use default intiial update and max step.
FreeformResilientPropagation(FreeformNetwork theNetwork, MLDataSet theTraining, double initialUpdate, double theMaxStep) Construct the RPROP trainer.

Method Summary

Methods

Modifier and Type	Method and Description
protected void	learnConnection(FreeformConnection connection) Learn for a single connection.
TrainingContinuation	pause() Pause the training to continue later.
void	resume(TrainingContinuation state) Resume training.

Methods inherited from class org.encog.neural.freeform.training.FreeformPropagationTraining

canContinue, finishTraining, getBatchSize, getError, getImplementationType, getIteration, getMethod, getTraining, isFixFlatSopt, iteration, iteration, learn, processBatches, processPureBatch, setBatchSize, setError, setFixFlatSopt, setIteration

Methods inherited from class org.encog.ml.train.BasicTraining

addStrategy, getStrategies, isTrainingDone, postIteration, preIteration, setTraining

Methods inherited from class java.lang.Object

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

Field Detail

TEMP_GRADIENT

public static final int TEMP_GRADIENT

Temp value #0: the gradient.

See Also:

Constant Field Values

TEMP_LAST_GRADIENT

public static final int TEMP_LAST_GRADIENT

Temp value #1: the last gradient.

See Also:

Constant Field Values

TEMP_UPDATE

public static final int TEMP_UPDATE

Temp value #2: the update.

See Also:

Constant Field Values

TEMP_LAST_WEIGHT_DELTA

public static final int TEMP_LAST_WEIGHT_DELTA

Temp value #3: the the last weight delta.

See Also:

Constant Field Values

Constructor Detail

FreeformResilientPropagation

public FreeformResilientPropagation(FreeformNetwork theNetwork,
                            MLDataSet theTraining)

Construct the RPROP trainer, Use default intiial update and max step.

Parameters:

theNetwork - The network to train.

theTraining - The training set.

FreeformResilientPropagation

public FreeformResilientPropagation(FreeformNetwork theNetwork,
                            MLDataSet theTraining,
                            double initialUpdate,
                            double theMaxStep)

Construct the RPROP trainer.

Parameters:

theNetwork - The network to train.

theTraining - The training set.

initialUpdate - The initial update.

theMaxStep - The max step.

Method Detail

learnConnection

protected void learnConnection(FreeformConnection connection)

Learn for a single connection.

Specified by:

learnConnection in class FreeformPropagationTraining

Parameters:

connection - The connection to learn from.

pause

public TrainingContinuation pause()

Pause the training to continue later.

Specified by:

pause in interface MLTrain

Returns:

A training continuation object.

resume

public void resume(TrainingContinuation state)

Resume training.

Specified by:

resume in interface MLTrain

Parameters:

state - The training continuation object to use to continue.