C# Class Encog.MathUtil.Randomize.GaussianRandomizer

Generally, you will not want to use this randomizer as a pure neural network randomizer. More on this later in the description. Generate random numbers that fall within a Gaussian curve. The mean represents the center of the curve, and the standard deviation helps determine the length of the curve on each side. This randomizer is used mainly for special cases where I want to generate random numbers in a Gaussian range. For a pure neural network initializer, it leaves much to be desired. However, it can make for a decent randomizer. Usually, the Nguyen Widrow randomizer performs better. Uses the "Box Muller" method. http://en.wikipedia.org/wiki/Box%E2%80%93Muller_transform Ported from C++ version provided by Everett F. Carter Jr., 1994

Inheritance: BasicRandomizer

Show file Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method	Description
BoxMuller ( double m, double s ) : double	Compute a Gaussian random number.
GaussianRandomizer ( double mean, double standardDeviation ) : System	Construct a Gaussian randomizer. The mean, the standard deviation.
Randomize ( double d ) : double	Generate a random number.

Method Details

BoxMuller() public method

Compute a Gaussian random number.

public BoxMuller ( double m, double s ) : double
m	double	The mean.
s	double	The standard deviation.
return	double

GaussianRandomizer() public method

Construct a Gaussian randomizer. The mean, the standard deviation.

public GaussianRandomizer ( double mean, double standardDeviation ) : System
mean	double	The mean.
standardDeviation	double	The standard deviation.
return	System

Randomize() public method

Generate a random number.

public Randomize ( double d ) : double
d	double	The input value, not used.
return	double