C# Class Encog.Neural.Networks.Training.Hopfield.TrainHopfield

This class is used to train a Hopfield neural network. A hopfield neural network can be created by using the basic layer and connecting it to itself, forming a single layer recurrent neural network. This is an unsupervised training algorithm. Ideal values should not be specified in the training set. If ideal values are present, they will be ignored.

Inheritance: BasicTraining

Exibir arquivo Open project: encog/encog-silverlight-core

Public Methods

Method	Description
Iteration ( ) : void	Perform one training iteration.
TrainHopfield ( INeuralDataSet trainingSet, BasicNetwork network ) : System	Construct a Hopfield training class.
TrainHopfieldSynapse ( ISynapse synapse, INeuralData pattern ) : void	Train the neural network for the specified pattern. The neural network can be trained for more than one pattern. To do this simply call the train method more than once.

Private Methods

Method	Description
ConvertHopfieldMatrix ( ISynapse target, Matrix delta ) : void
TrainHopfieldSynapse ( ISynapse recurrent ) : void	Once the hopfield synapse has been found, this method is called to train it.

Method Details

Iteration() public method

Perform one training iteration.

public Iteration ( ) : void
return	void

TrainHopfield() public method

Construct a Hopfield training class.

public TrainHopfield ( INeuralDataSet trainingSet, BasicNetwork network ) : System
trainingSet	INeuralDataSet	The training set to use.
network	BasicNetwork	The network to train.
return	System

TrainHopfieldSynapse() public method

Train the neural network for the specified pattern. The neural network can be trained for more than one pattern. To do this simply call the train method more than once.

public TrainHopfieldSynapse ( ISynapse synapse, INeuralData pattern ) : void
synapse	ISynapse	The synapse to train.
pattern	INeuralData	The pattern to train for.
return	void