C# Class Encog.Neural.Flat.Train.Prop.TrainFlatNetworkManhattan

Train the flat network using Manhattan update rule.

Inheritance: TrainFlatNetworkProp

Show file Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method	Description
InitOthers ( ) : void	Not needed for this training type.
TrainFlatNetworkManhattan ( FlatNetwork network, IMLDataSet training, double theLearningRate ) : System	Construct a trainer for flat networks to use the Manhattan update rule.
UpdateWeight ( double gradients, double lastGradient, int index ) : double	Calculate the amount to change the weight by.

Method Details

InitOthers() public method

Not needed for this training type.

public InitOthers ( ) : void
return	void

TrainFlatNetworkManhattan() public method

Construct a trainer for flat networks to use the Manhattan update rule.

public TrainFlatNetworkManhattan ( FlatNetwork network, IMLDataSet training, double theLearningRate ) : System
network	FlatNetwork	The network to train.
training	IMLDataSet	The training data to use.
theLearningRate	double	The learning rate to use.
return	System

UpdateWeight() public final method

Calculate the amount to change the weight by.

public final UpdateWeight ( double gradients, double lastGradient, int index ) : double
gradients	double	The gradients.
lastGradient	double	The last gradients.
index	int	The index to update.
return	double