C# 클래스 Encog.Engine.Network.Train.Prop.TrainFlatNetworkSCG

Train a network using scaled conjugate gradient.

상속: TrainFlatNetworkProp

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

공개 메소드들

메소드	설명
CalculateGradients ( ) : void	Calculate the gradients. They are normalized as well.
Iteration ( ) : void	Perform one iteration.
TrainFlatNetworkSCG ( FlatNetwork network, IEngineDataSet training ) : Encog.Engine.Data	Construct the training object.
UpdateWeight ( double gradients, double lastGradient, int index ) : double	Update the weights.

비공개 메소드들

메소드	설명
Init ( ) : void	Calculate the starting set of gradients.

메소드 상세

CalculateGradients() 공개 메소드

Calculate the gradients. They are normalized as well.

public CalculateGradients ( ) : void
리턴	void

Iteration() 공개 메소드

Perform one iteration.

public Iteration ( ) : void
리턴	void

TrainFlatNetworkSCG() 공개 메소드

Construct the training object.

public TrainFlatNetworkSCG ( FlatNetwork network, IEngineDataSet training ) : Encog.Engine.Data
network	Encog.Engine.Network.Flat.FlatNetwork	The network to train.
training	IEngineDataSet	The training data to use.
리턴	Encog.Engine.Data

UpdateWeight() 공개 메소드

Update the weights.

public UpdateWeight ( double gradients, double lastGradient, int index ) : double
gradients	double	The current gradients.
lastGradient	double	The last gradients.
index	int	The index.
리턴	double