org.encog.ml.train.strategy.end

Class EarlyStoppingStrategy

java.lang.Object

org.encog.ml.train.strategy.end.EarlyStoppingStrategy

All Implemented Interfaces:

EndTrainingStrategy, Strategy

public class EarlyStoppingStrategy
extends java.lang.Object
implements EndTrainingStrategy

A simple early stopping strategy that halts training when the validation set no longer improves.

Constructor Summary

Constructors

Constructor and Description
EarlyStoppingStrategy(MLDataSet theValidationSet)
EarlyStoppingStrategy(MLDataSet theValidationSet, int theCheckFrequency, int theAllowedStagnantIterations)

Method Summary

Modifier and Type	Method and Description
int	getAllowedStagnantIterations()
MLRegression	getBestModel()
double	getBestValidationError()
double	getMinimumImprovement()
int	getStagnantIterations()
double	getTrainingError()
double	getValidationError()
void	init(MLTrain theTrain) Initialize this strategy.
boolean	isSaveBest()
void	postIteration() Called just after a training iteration.
void	preIteration() Called just before a training iteration.
void	setAllowedStagnantIterations(int allowedStagnantIterations)
void	setMinimumImprovement(double minimumImprovement)
void	setSaveBest(boolean saveBest)
void	setStagnantIterations(int stagnantIterations)
boolean	shouldStop()

Methods inherited from class java.lang.Object

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

Constructor Detail

EarlyStoppingStrategy

public EarlyStoppingStrategy(MLDataSet theValidationSet)

EarlyStoppingStrategy

public EarlyStoppingStrategy(MLDataSet theValidationSet,
                             int theCheckFrequency,
                             int theAllowedStagnantIterations)

Method Detail

init

public void init(MLTrain theTrain)

Initialize this strategy.

Specified by:

init in interface Strategy

Parameters:

theTrain - The training algorithm.

preIteration

public void preIteration()

Called just before a training iteration.

Specified by:

preIteration in interface Strategy

postIteration

public void postIteration()

Called just after a training iteration.

Specified by:

postIteration in interface Strategy

shouldStop

public boolean shouldStop()

Specified by:

shouldStop in interface EndTrainingStrategy

Returns:

Returns true if we should stop.

getTrainingError

public double getTrainingError()

Returns:

the trainingError

getValidationError

public double getValidationError()

Returns:

The validation error.

getStagnantIterations

public int getStagnantIterations()

setStagnantIterations

public void setStagnantIterations(int stagnantIterations)

getAllowedStagnantIterations

public int getAllowedStagnantIterations()

setAllowedStagnantIterations

public void setAllowedStagnantIterations(int allowedStagnantIterations)

isSaveBest

public boolean isSaveBest()

setSaveBest

public void setSaveBest(boolean saveBest)

getBestModel

public MLRegression getBestModel()

getBestValidationError

public double getBestValidationError()

getMinimumImprovement

public double getMinimumImprovement()

setMinimumImprovement

public void setMinimumImprovement(double minimumImprovement)