org.encog.neural.networks.training
Class BasicTraining

java.lang.Object
  org.encog.neural.networks.training.BasicTraining

All Implemented Interfaces:

Train

Direct Known Subclasses:

CompetitiveTraining, CrossTraining, HebbianTraining, LevenbergMarquardtTraining, NeuralGeneticAlgorithm, NeuralSimulatedAnnealing, Propagation, SVDTraining, SVMTrain, TrainAdaline, TrainInstar, TrainOutstar

public abstract class BasicTraining
extends Object
implements Train

An abstract class that implements basic training for most training algorithms. Specifically training strategies can be added to enhance the training.

Author:

jheaton

Constructor Summary

BasicTraining()

Method Summary

void	addStrategy(Strategy strategy) Training strategies can be added to improve the training results.
void	finishTraining() Should be called after training has completed and the iteration method will not be called any further.
EncogCloud	getCloud()
double	getError() Get the current error percent from the training.
int	getIteration()
List<Strategy>	getStrategies()
NeuralDataSet	getTraining()
boolean	isTrainingDone()
void	iteration(int count) Perform the specified number of training iterations.
void	postIteration() Call the strategies after an iteration.
void	preIteration() Call the strategies before an iteration.
void	setCloud(EncogCloud cloud) Set the cloud use to track this training.
void	setError(double error)
void	setIteration(int iteration) Set the current training iteration.
void	setTraining(NeuralDataSet training) Set the training object that this strategy is working with.

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.encog.neural.networks.training.Train

getNetwork, iteration

Constructor Detail

BasicTraining

public BasicTraining()

Method Detail

addStrategy

public void addStrategy(Strategy strategy)

Training strategies can be added to improve the training results. There are a number to choose from, and several can be used at once.

Specified by:

addStrategy in interface Train

Parameters:

strategy - The strategy to add.

finishTraining

public void finishTraining()

Should be called after training has completed and the iteration method will not be called any further.

Specified by:

finishTraining in interface Train

getCloud

public EncogCloud getCloud()

Specified by:

getCloud in interface Train

Returns:

The cloud used to track this training.

getError

public double getError()

Get the current error percent from the training.

Specified by:

getError in interface Train

Returns:

The current error.

getIteration

public int getIteration()

Specified by:

getIteration in interface Train

Returns:

the iteration

getStrategies

public List<Strategy> getStrategies()

Specified by:

getStrategies in interface Train

Returns:

The strategies to use.

getTraining

public NeuralDataSet getTraining()

Specified by:

getTraining in interface Train

Returns:

The training data to use.

isTrainingDone

public boolean isTrainingDone()

Specified by:

isTrainingDone in interface Train

Returns:

True if training can progress no further.

iteration

public void iteration(int count)

Perform the specified number of training iterations. This is a basic implementation that just calls iteration the specified number of times. However, some training methods, particularly with the GPU, benefit greatly by calling with higher numbers than 1.

Specified by:

iteration in interface Train

Parameters:

count - The number of training iterations.

postIteration

public void postIteration()

Call the strategies after an iteration.

preIteration

public void preIteration()

Call the strategies before an iteration.

setCloud

public void setCloud(EncogCloud cloud)

Set the cloud use to track this training.

Specified by:

setCloud in interface Train

Parameters:

cloud - The cloud.

setError

public void setError(double error)

Specified by:

setError in interface Train

Parameters:

error - Set the current error rate. This is usually used by training strategies.

setIteration

public void setIteration(int iteration)

Description copied from interface: Train

Set the current training iteration.

Specified by:

setIteration in interface Train

Parameters:

iteration - the iteration to set

setTraining

public void setTraining(NeuralDataSet training)

Set the training object that this strategy is working with.

Parameters:

training - The training object.