C# Класс Encog.Neural.Flat.Train.Prop.TrainFlatNetworkBackPropagation

Наследование: TrainFlatNetworkProp
Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод Описание
InitOthers ( ) : void

Not needed for this training type.
TrainFlatNetworkBackPropagation ( FlatNetwork network, IMLDataSet training, double theLearningRate, double theMomentum ) : Encog.ML.Data

Construct a backprop trainer for flat networks.
UpdateWeight ( double gradients, double lastGradient, int index ) : double

Update a weight.

Описание методов

InitOthers() публичный Метод

Not needed for this training type.
public InitOthers ( ) : void
Результат void

TrainFlatNetworkBackPropagation() публичный Метод

Construct a backprop trainer for flat networks.
public TrainFlatNetworkBackPropagation ( FlatNetwork network, IMLDataSet training, double theLearningRate, double theMomentum ) : Encog.ML.Data
network Encog.Neural.Flat.FlatNetwork The network to train.
training IMLDataSet The training data.
theLearningRate double The learning rate.
theMomentum double The momentum.
Результат Encog.ML.Data

UpdateWeight() публичный закрытый Метод

Update a weight.
public final UpdateWeight ( double gradients, double lastGradient, int index ) : double
gradients double The gradients.
lastGradient double The last gradients.
index int The index.
Результат double