C# Class Encog.ML.Train.BasicTraining

An abstract class that implements basic training for most training algorithms. Specifically training strategies can be added to enhance the training.

Inheritance: IMLTrain

显示文件 Open project: encog/encog-silverlight-core

Public Methods

Method	Description
AddStrategy ( IStrategy strategy ) : void	Training strategies can be added to improve the training results. There are a number to choose from, and several can be used at once.
FinishTraining ( ) : void	Should be called after training has completed and the iteration method will not be called any further.
Iteration ( ) : void	from Encog.ml.train.MLTrain
Iteration ( int count ) : void	Perform the specified number of training iterations. This is a basic implementation that just calls iteration the specified number of times. However, some training methods, particularly with the GPU, benefit greatly by calling with higher numbers than 1.
Pause ( ) : TrainingContinuation	from Encog.ml.train.MLTrain
PostIteration ( ) : void	Call the strategies after an iteration.
PreIteration ( ) : void	Call the strategies before an iteration.
Resume ( TrainingContinuation state ) : void	from Encog.ml.train.MLTrain

Protected Methods

Method	Description
BasicTraining ( TrainingImplementationType implementationType ) : System.Collections.Generic	Construct the object, specify the implementation type.

Method Details

AddStrategy() public method

Training strategies can be added to improve the training results. There are a number to choose from, and several can be used at once.

public AddStrategy ( IStrategy strategy ) : void
strategy	IStrategy	The strategy to add.
return	void

BasicTraining() protected method

Construct the object, specify the implementation type.

protected BasicTraining ( TrainingImplementationType implementationType ) : System.Collections.Generic
implementationType	TrainingImplementationType
return	System.Collections.Generic

FinishTraining() public method

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

public FinishTraining ( ) : void
return	void

Iteration() public abstract method

from Encog.ml.train.MLTrain

public abstract Iteration ( ) : void
return	void

Iteration() public method

Perform the specified number of training iterations. This is a basic implementation that just calls iteration the specified number of times. However, some training methods, particularly with the GPU, benefit greatly by calling with higher numbers than 1.

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

Pause() public abstract method

from Encog.ml.train.MLTrain

public abstract Pause ( ) : TrainingContinuation
return	Encog.Neural.Networks.Training.Propagation.TrainingContinuation

PostIteration() public method

Call the strategies after an iteration.

public PostIteration ( ) : void
return	void

PreIteration() public method

Call the strategies before an iteration.

public PreIteration ( ) : void
return	void

Resume() public abstract method

from Encog.ml.train.MLTrain

public abstract Resume ( TrainingContinuation state ) : void
state	Encog.Neural.Networks.Training.Propagation.TrainingContinuation
return	void