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

상속: ITrainFlatNetwork

파일 보기 프로젝트 열기: encog/encog-silverlight-core 1 사용 예제들

보호된 프로퍼티들

프로퍼티	타입	설명
CurrentError	double
Gradients	double[]

공개 메소드들

메소드	설명
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.

보호된 메소드들

메소드	설명
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.

비공개 메소드들

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

메소드 상세

CalculateGradients() 공개 메소드

Calculate the gradients.

public CalculateGradients ( ) : void
리턴	void

FinishTraining() 공개 메소드

public FinishTraining ( ) : void
리턴	void

InitOthers() 공개 추상적인 메소드

Allow other training methods to init.

public abstract InitOthers ( ) : void
리턴	void

Iteration() 공개 메소드

public Iteration ( ) : void
리턴	void

Iteration() 공개 메소드

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.
리턴	void

Learn() 보호된 메소드

Apply and learn.

protected Learn ( ) : void
리턴	void

LearnLimited() 보호된 메소드

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
리턴	void

Report() 공개 메소드

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.
리턴	void

TrainFlatNetworkProp() 보호된 메소드

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.
리턴	System

UpdateWeight() 공개 추상적인 메소드

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.
리턴	double

프로퍼티 상세

CurrentError 보호되어 있는 프로퍼티

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

protected double CurrentError
리턴	double

Gradients 보호되어 있는 프로퍼티

The gradients.

protected double[] Gradients
리턴	double[]