C# 클래스 Encog.ML.Train.Strategy.ResetStrategy

The reset strategy will reset the weights if the neural network fails to fall below a specified error by a specified number of cycles. This can be useful to throw out initially "bad/hard" random initializations of the weight matrix.

상속: IStrategy

파일 보기 프로젝트 열기: encog/encog-silverlight-core

공개 메소드들

메소드	설명
Init ( IMLTrain train ) : void	Initialize this strategy.
PostIteration ( ) : void	Called just after a training iteration.
PreIteration ( ) : void	Called just before a training iteration.
ResetStrategy ( double required, int cycles ) : Encog.Neural.Networks.Training	Construct a reset strategy. The error rate must fall below the required rate in the specified number of cycles, or the neural network will be reset to random weights and bias values.

메소드 상세

Init() 공개 메소드

Initialize this strategy.

public Init ( IMLTrain train ) : void
train	IMLTrain	The training algorithm.
리턴	void

PostIteration() 공개 메소드

Called just after a training iteration.

public PostIteration ( ) : void
리턴	void

PreIteration() 공개 메소드

Called just before a training iteration.

public PreIteration ( ) : void
리턴	void

ResetStrategy() 공개 메소드

Construct a reset strategy. The error rate must fall below the required rate in the specified number of cycles, or the neural network will be reset to random weights and bias values.

public ResetStrategy ( double required, int cycles ) : Encog.Neural.Networks.Training
required	double	The required error rate.
cycles	int	The number of cycles to reach that rate.
리턴	Encog.Neural.Networks.Training