C# Class Encog.Neural.Networks.Training.Strategy.StopTrainingStrategy

This strategy will indicate once training is no longer improving the neural network by a specified amount, over a specified number of cycles. This allows the program to automatically determine when to stop training.

Inheritance: IStrategy

Datei anzeigen Open project: encog/encog-silverlight-core

Public Methods

Method	Description
Init ( ITrain train ) : void	Initialize this strategy.
PostIteration ( ) : void	Called just after a training iteration.
PreIteration ( ) : void	Called just before a training iteration.
ShouldStop ( ) : bool	True if training should stop.
StopTrainingStrategy ( ) : System	Construct the strategy with default options.
StopTrainingStrategy ( double minImprovement, int toleratedCycles ) : System	Construct the strategy with the specified parameters.

Method Details

Init() public method

Initialize this strategy.

public Init ( ITrain train ) : void
train	ITrain	The training algorithm.
return	void

PostIteration() public method

Called just after a training iteration.

public PostIteration ( ) : void
return	void

PreIteration() public method

Called just before a training iteration.

public PreIteration ( ) : void
return	void

ShouldStop() public method

True if training should stop.

public ShouldStop ( ) : bool
return	bool

StopTrainingStrategy() public method

Construct the strategy with default options.

public StopTrainingStrategy ( ) : System
return	System

StopTrainingStrategy() public method

Construct the strategy with the specified parameters.

public StopTrainingStrategy ( double minImprovement, int toleratedCycles ) : System
minImprovement	double	The minimum accepted improvement.
toleratedCycles	int	The number of cycles to tolerate before stopping.
return	System