C# 클래스 Encog.MathUtil.Randomize.NguyenWidrowRandomizer

Implementation of Nguyen-Widrow weight initialization. This is the default weight initialization used by Encog, as it generally provides the most trainable neural network.

상속: IRandomizer

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

공개 메소드들

메소드	설명
NguyenWidrowRandomizer ( double min, double max ) : System	Construct a Nguyen-Widrow randomizer.
Randomize ( BasicNetwork network, int fromLayer ) : void	Randomize one level of a neural network.
Randomize ( IMLMethod method ) : void	The Nguyen-Widrow initialization algorithm is the following : 1. Initialize all weight of hidden layers with (ranged) random values 2. For each hidden layer 2.1 calculate beta value, 0.7/// Nth(#neurons of input layer) root of #neurons of current layer 2.2 for each synapse 2.1.1 for each weight 2.1.2 Adjust weight by dividing by norm of weight for neuron and multiplying by beta value

메소드 상세

NguyenWidrowRandomizer() 공개 메소드

Construct a Nguyen-Widrow randomizer.

public NguyenWidrowRandomizer ( double min, double max ) : System
min	double	The min of the range.
max	double	The max of the range.
리턴	System

Randomize() 공개 메소드

Randomize one level of a neural network.

public Randomize ( BasicNetwork network, int fromLayer ) : void
network	Encog.Neural.Networks.BasicNetwork	The network to randomize
fromLayer	int	The from level to randomize.
리턴	void

Randomize() 공개 최종 메소드

The Nguyen-Widrow initialization algorithm is the following : 1. Initialize all weight of hidden layers with (ranged) random values 2. For each hidden layer 2.1 calculate beta value, 0.7/// Nth(#neurons of input layer) root of #neurons of current layer 2.2 for each synapse 2.1.1 for each weight 2.1.2 Adjust weight by dividing by norm of weight for neuron and multiplying by beta value

public final Randomize ( IMLMethod method ) : void
method	IMLMethod	The network to randomize.
리턴	void