C# Class Encog.Engine.Network.Train.Prop.TrainFlatNetworkManhattan

Train the flat network using Manhattan update rule.
Inheritance: TrainFlatNetworkProp
Afficher le fichier Open project: encog/encog-silverlight-core Class Usage Examples

Méthodes publiques

Méthode Description
TrainFlatNetworkManhattan ( FlatNetwork network, IEngineDataSet training, double learningRate ) : Encog.Engine.Data

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

TrainFlatNetworkManhattan() public méthode

Construct a trainer for flat networks to use the Manhattan update rule.
public TrainFlatNetworkManhattan ( FlatNetwork network, IEngineDataSet training, double learningRate ) : Encog.Engine.Data
network Encog.Engine.Network.Flat.FlatNetwork The network to train.
training IEngineDataSet The training data to use.
learningRate double The learning rate to use.
Résultat Encog.Engine.Data

UpdateWeight() public méthode

Calculate the amount to change the weight by.
public UpdateWeight ( double gradients, double lastGradient, int index ) : double
gradients double The gradients.
lastGradient double The last gradients.
index int The index to update.
Résultat double