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

Наследование: IEngineTask

Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод	Описание
GradientWorker ( FlatNetwork theNetwork, TrainFlatNetworkProp theOwner, IMLDataSet theTraining, int theLow, int theHigh, double theFlatSpots, IErrorFunction ef ) : System	Construct a gradient worker.
Run ( ) : void	Perform the gradient calculation for the specified index range.

Приватные методы

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

Описание методов

GradientWorker() публичный Метод

Construct a gradient worker.

public GradientWorker ( FlatNetwork theNetwork, TrainFlatNetworkProp theOwner, IMLDataSet theTraining, int theLow, int theHigh, double theFlatSpots, IErrorFunction ef ) : System
theNetwork	Encog.Neural.Flat.FlatNetwork	The network to train.
theOwner	TrainFlatNetworkProp	The owner that is doing the training.
theTraining	IMLDataSet	The training data.
theLow	int	The low index to use in the training data.
theHigh	int	The high index to use in the training data.
theFlatSpots	double	Holds an array of flat spot constants.
ef	IErrorFunction
Результат	System

Run() публичный Метод

Perform the gradient calculation for the specified index range.

public Run ( ) : void
Результат	void