C# Class Encog.MathUtil.Equilateral

Used to produce an array of activations to classify data into groups. This class is provided the number of groups, as well as the range that the activations should fall into.

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

Public Methods

Method	Description
Decode ( double activations ) : int	Decode a set of activations and see which set it has the lowest Euclidean distance from.
Encode ( int set ) : double[]	Get the activations for the specified set.
Equilateral ( int count, double high, double low ) : System	Construct an equilateral matrix.
GetDistance ( double data, int set ) : double	Get the Euclidean distance between the specified data and the set number.
GetSmallestDistance ( double data ) : int	Get the smallest distance.

Private Methods

Method	Description
Equilat ( int n, double high, double low ) : double[][]	Called internally to generate the matrix.

Method Details

Decode() public method

Decode a set of activations and see which set it has the lowest Euclidean distance from.

public Decode ( double activations ) : int
activations	double	The output from the neural network.
return	int

Encode() public method

Get the activations for the specified set.

public Encode ( int set ) : double[]
set	int	The set to determine the activations for.
return	double[]

Equilateral() public method

Construct an equilateral matrix.

public Equilateral ( int count, double high, double low ) : System
count	int	The number of sets, these will be the rows in the matrix.
high	double	The high value for the outputs.
low	double	The low value for the outputs.
return	System

GetDistance() public method

Get the Euclidean distance between the specified data and the set number.

public GetDistance ( double data, int set ) : double
data	double	The data to check.
set	int	The set to check.
return	double

GetSmallestDistance() public method

Get the smallest distance.

public GetSmallestDistance ( double data ) : int
data	double	The data to check.
return	int