C# Class Encog.Neural.Flat.Train.Prop.TrainFlatNetworkProp

Inheritance: ITrainFlatNetwork

Afficher le fichier Open project: encog/encog-silverlight-core Class Usage Examples

Protected Properties

Свойство	Type	Description
CurrentError	double
Gradients	double[]

Méthodes publiques

Méthode	Description
CalculateGradients ( ) : void	Calculate the gradients.
FinishTraining ( ) : void
InitOthers ( ) : void	Allow other training methods to init.
Iteration ( ) : void
Iteration ( int count ) : void	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.
Report ( double gradients, double error, Exception ex ) : void	Called by the worker threads to report the progress at each step.
UpdateWeight ( double gradients, double lastGradient, int index ) : double	Update a weight, the means by which weights are updated vary depending on the training.

Méthodes protégées

Méthode	Description
Learn ( ) : void	Apply and learn.
LearnLimited ( ) : void	Apply and learn. This is the same as learn, but it checks to see if any of the weights are below the limit threshold. In this case, these weights are zeroed out. Having two methods allows the regular learn method, which is what is usually use, to be as fast as possible.
TrainFlatNetworkProp ( FlatNetwork network, IMLDataSet training ) : System	Train a flat network multithreaded.

Private Methods

Méthode	Description
CopyContexts ( ) : void	Copy the contexts to keep them consistent with multithreaded training.
Init ( ) : void	Init the process.

Method Details

CalculateGradients() public méthode

Calculate the gradients.

public CalculateGradients ( ) : void
Résultat	void

FinishTraining() public méthode

public FinishTraining ( ) : void
Résultat	void

InitOthers() public abstract méthode

Allow other training methods to init.

public abstract InitOthers ( ) : void
Résultat	void

Iteration() public méthode

public Iteration ( ) : void
Résultat	void

Iteration() public méthode

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.

public Iteration ( int count ) : void
count	int	The number of training iterations.
Résultat	void

Learn() protected méthode

Apply and learn.

protected Learn ( ) : void
Résultat	void

LearnLimited() protected méthode

Apply and learn. This is the same as learn, but it checks to see if any of the weights are below the limit threshold. In this case, these weights are zeroed out. Having two methods allows the regular learn method, which is what is usually use, to be as fast as possible.

protected LearnLimited ( ) : void
Résultat	void

Report() public méthode

Called by the worker threads to report the progress at each step.

public Report ( double gradients, double error, Exception ex ) : void
gradients	double	The gradients from that worker.
error	double	The error for that worker.
ex	System.Exception	The exception.
Résultat	void

TrainFlatNetworkProp() protected méthode

Train a flat network multithreaded.

protected TrainFlatNetworkProp ( FlatNetwork network, IMLDataSet training ) : System
network	Encog.Neural.Flat.FlatNetwork	The network to train.
training	IMLDataSet	The training data to use.
Résultat	System

UpdateWeight() public abstract méthode

Update a weight, the means by which weights are updated vary depending on the training.

public abstract UpdateWeight ( double gradients, double lastGradient, int index ) : double
gradients	double	The gradients.
lastGradient	double	The last gradients.
index	int	The index.
Résultat	double

Property Details

CurrentError protected_oe property

The current error is the average error over all of the threads.

protected double CurrentError
Résultat	double

Gradients protected_oe property

The gradients.

protected double[] Gradients
Résultat	double[]