C# Class AForge.Neuro.Learning.ElasticNetworkLearning

Elastic network learning algorithm.

This class implements elastic network's learning algorithm and allows to train Distance Networks.

Inheritance: IUnsupervisedLearning

显示文件 Open project: holisticware-admin/MonoVersal.AForgeNET Class Usage Examples

Public Methods

Method	Description
ElasticNetworkLearning ( DistanceNetwork network ) : System	Initializes a new instance of the ElasticNetworkLearning class.
Run ( double input ) : double	Runs learning iteration. The method runs one learning iterations - finds winner neuron (the neuron which has weights with values closest to the specified input vector) and updates its weight (as well as weights of neighbor neurons) in the way to decrease difference with the specified input vector.
RunEpoch ( double input ) : double	Runs learning epoch. The method runs one learning epoch, by calling Run method for each vector provided in the input array.

Method Details

ElasticNetworkLearning() public method

Initializes a new instance of the ElasticNetworkLearning class.

public ElasticNetworkLearning ( DistanceNetwork network ) : System
network	DistanceNetwork	Neural network to train.
return	System

Run() public method

Runs learning iteration.

The method runs one learning iterations - finds winner neuron (the neuron which has weights with values closest to the specified input vector) and updates its weight (as well as weights of neighbor neurons) in the way to decrease difference with the specified input vector.

public Run ( double input ) : double
input	double	Input vector.
return	double

RunEpoch() public method

Runs learning epoch.

The method runs one learning epoch, by calling Run method for each vector provided in the input array.

public RunEpoch ( double input ) : double
input	double	Array of input vectors.
return	double