C# Class Encog.Neural.Networks.Training.PNN.GlobalMinimumSearch

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

Méthodes publiques

Méthode	Description
Brentmin ( int maxIterations, double maxError, double eps, double tol, ICalculationCriteria network, double y ) : double	Use the "Brent Method" to find a better minimum.
FindBestRange ( double low, double high, int numberOfPoints, bool useLog, double minError, ICalculationCriteria network ) : void	Find the best common gamma. Use the same gamma for all kernels. This is a crude brute-force search. The range found should be refined using the "Brent Method", also provided in this class.

Method Details

Brentmin() public méthode

Use the "Brent Method" to find a better minimum.

public Brentmin ( int maxIterations, double maxError, double eps, double tol, ICalculationCriteria network, double y ) : double
maxIterations	int	THe maximum number of iterations.
maxError	double	We can stop if we reach this error.
eps	double	The approximate machine precision.
tol	double	Brent's tolerance, must be >= sqrt( eps )
network	ICalculationCriteria	The network to obtain the error from.
y	double	The error at x2.
Résultat	double

FindBestRange() public méthode

Find the best common gamma. Use the same gamma for all kernels. This is a crude brute-force search. The range found should be refined using the "Brent Method", also provided in this class.

public FindBestRange ( double low, double high, int numberOfPoints, bool useLog, double minError, ICalculationCriteria network ) : void
low	double	The low gamma to begin the search with.
high	double	The high gamma to end the search with.
numberOfPoints	int	If you do set this to negative, set x2 and y2 to the correct values.
useLog	bool	Should we progress "logarithmically" from low to high.
minError	double	We are done if the error is below this.
network	ICalculationCriteria	The network to evaluate.
Résultat	void