C# Класс Encog.Engine.Network.Train.Gradient.GradientWorkerCPU

Worker class for the mulithreaded training of flat networks.

Наследование: IFlatGradientWorker

Показать файл Открыть проект

Открытые методы

Метод	Описание
GradientWorkerCPU ( FlatNetwork network, TrainFlatNetworkProp owner, IEngineIndexableSet training, int low, int high ) : Encog.Engine.Data	Construct a gradient worker.
Run ( ) : void	Perform the gradient calculation for the specified index range.

Приватные методы

Метод	Описание
Process ( double input, double ideal ) : void	Process one training set element.
ProcessLevel ( int currentLevel ) : void	Process one level.

Описание методов

GradientWorkerCPU() публичный Метод

Construct a gradient worker.

public GradientWorkerCPU ( FlatNetwork network, TrainFlatNetworkProp owner, IEngineIndexableSet training, int low, int high ) : Encog.Engine.Data
network	Encog.Engine.Network.Flat.FlatNetwork	The network to train.
owner	Encog.Engine.Network.Train.Prop.TrainFlatNetworkProp	The owner that is doing the training.
training	IEngineIndexableSet	The training data.
low	int	The low index to use in the training data.
high	int	The high index to use in the training data.
Результат	Encog.Engine.Data

Run() публичный Метод

Perform the gradient calculation for the specified index range.

public Run ( ) : void
Результат	void