C# Class Encog.Neural.Networks.Training.Competitive.BestMatchingUnit

The "Best Matching Unit" or BMU is a very important concept in the training for a SOM. The BMU is the output neuron that has weight connections to the input neurons that most closely match the current input vector. This neuron (and its "neighborhood") are the neurons that will receive training. This class also tracks the worst distance (of all BMU's). This gives some indication of how well the network is trained, and thus becomes the "error" of the entire network.

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

Méthodes publiques

Méthode	Description
BestMatchingUnit ( CompetitiveTraining training ) : System	Construct a BestMatchingUnit class. The training class must be provided.
CalculateBMU ( ISynapse synapse, INeuralData input ) : int	Calculate the best matching unit (BMU). This is the output neuron that has the lowest Euclidean distance to the input vector.
CalculateEuclideanDistance ( ISynapse synapse, INeuralData input, int outputNeuron ) : double	Calculate the Euclidean distance for the specified output neuron and the input vector. This is the square root of the squares of the differences between the weight and input vectors.
Reset ( ) : void	Reset the "worst distance" back to a minimum value. This should be called for each training iteration.

Method Details

BestMatchingUnit() public méthode

Construct a BestMatchingUnit class. The training class must be provided.

public BestMatchingUnit ( CompetitiveTraining training ) : System
training	CompetitiveTraining	The parent class.
Résultat	System

CalculateBMU() public méthode

Calculate the best matching unit (BMU). This is the output neuron that has the lowest Euclidean distance to the input vector.

public CalculateBMU ( ISynapse synapse, INeuralData input ) : int
synapse	ISynapse	The synapse to calculate for.
input	INeuralData	The input vector.
Résultat	int

CalculateEuclideanDistance() public méthode

Calculate the Euclidean distance for the specified output neuron and the input vector. This is the square root of the squares of the differences between the weight and input vectors.

public CalculateEuclideanDistance ( ISynapse synapse, INeuralData input, int outputNeuron ) : double
synapse	ISynapse	The synapse to get the weights from.
input	INeuralData	The input vector.
outputNeuron	int	The neuron we are calculating the distance for.
Résultat	double

Reset() public méthode

Reset the "worst distance" back to a minimum value. This should be called for each training iteration.

public Reset ( ) : void
Résultat	void