C# Class Encog.Neural.Networks.Training.Propagation.Propagation

Implements basic functionality that is needed by each of the propagation methods. The specifics of each of the propagation methods is implemented inside of the PropagationMethod interface implementors.

Inheritance: Encog.ML.Train.BasicTraining, ITrain, IMultiThreadable

Exibir arquivo Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method	Description
FinishTraining ( ) : void	Should be called after training has completed and the iteration method will not be called any further.
Iteration ( ) : void	Perform one training iteration.
Iteration ( int count ) : void	Perform the specified number of training iterations. This can be more efficient than single training iterations. This is particularly true if you are training with a GPU.

Protected Methods

Method	Description
Propagation ( IContainsFlat network, IMLDataSet training ) : System	Construct a propagation object.

Method Details

FinishTraining() public final method

Should be called after training has completed and the iteration method will not be called any further.

public final FinishTraining ( ) : void
return	void

Iteration() public final method

Perform one training iteration.

public final Iteration ( ) : void
return	void

Iteration() public final method

Perform the specified number of training iterations. This can be more efficient than single training iterations. This is particularly true if you are training with a GPU.

public final Iteration ( int count ) : void
count	int	The number of training iterations.
return	void

Propagation() protected method

Construct a propagation object.

protected Propagation ( IContainsFlat network, IMLDataSet training ) : System
network	IContainsFlat	The network.
training	IMLDataSet	The training set.
return	System