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

Наследование: TrainFlatNetworkProp
Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод Описание
InitOthers ( ) : void

Called to init the QPROP.
TrainFlatNetworkQPROP ( FlatNetwork network, IMLDataSet training, double theLearningRate ) : Encog.ML.Data

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

Update a weight.

Описание методов

InitOthers() публичный Метод

Called to init the QPROP.
public InitOthers ( ) : void
Результат void

TrainFlatNetworkQPROP() публичный Метод

Construct a QPROP trainer for flat networks.
public TrainFlatNetworkQPROP ( FlatNetwork network, IMLDataSet training, double theLearningRate ) : Encog.ML.Data
network Encog.Neural.Flat.FlatNetwork The network to train.
training IMLDataSet The training data.
theLearningRate double The learning rate. 2 is a good suggestion as /// a learning rate to start with. If it fails to converge, /// then drop it. Just like backprop, except QPROP can /// take higher learning rates.
Результат Encog.ML.Data

UpdateWeight() публичный Метод

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