C# Class Encog.Neural.Networks.Pattern.BAMPattern

Construct a Bidirectional Access Memory (BAM) neural network. This neural network type learns to associate one pattern with another. The two patterns do not need to be of the same length. This network has two that are connected to each other. Though they are labeled as input and output layers to Encog, they are both equal, and should simply be thought of as the two layers that make up the net.

Inheritance: INeuralNetworkPattern

Afficher le fichier Open project: encog/encog-silverlight-core

Méthodes publiques

Свойство	Type	Description
TAG_F1	String
TAG_F2	String

Méthodes publiques

Méthode	Description
AddHiddenLayer ( int count ) : void	Unused, a BAM has no hidden layers.
Clear ( ) : void	Clear any settings on the pattern.
Generate ( ) : BasicNetwork	The generated network.

Method Details

AddHiddenLayer() public méthode

Unused, a BAM has no hidden layers.

public AddHiddenLayer ( int count ) : void
count	int	Not used.
Résultat	void

Clear() public méthode

Clear any settings on the pattern.

public Clear ( ) : void
Résultat	void

Generate() public méthode

The generated network.

public Generate ( ) : BasicNetwork
Résultat	BasicNetwork

Property Details

TAG_F1 public_oe static_oe property

The F1 layer.

public static String TAG_F1
Résultat	String

TAG_F2 public_oe static_oe property

The F2 layer.

public static String TAG_F2
Résultat	String