C# Класс Encog.Neural.Networks.Training.Strategy.HybridStrategy

A hybrid stragey allows a secondary training algorithm to be used. Once the primary algorithm is no longer improving by much, the secondary will be used. Using simulated annealing in as a secondary to one of the propagation methods is often a very efficient combination as it can help the propagation method escape a local minimum. This is particularly true with backpropagation.

Наследование: IStrategy

Показать файл Открыть проект

Открытые методы

Метод	Описание
HybridStrategy ( ITrain altTrain ) : System	Construct a hybrid strategy with the default minimum improvement and toleration cycles.
HybridStrategy ( ITrain altTrain, double minImprovement, int tolerateMinImprovement, int alternateCycles ) : System	Create a hybrid strategy.
Init ( ITrain train ) : void	Initialize this strategy.
PostIteration ( ) : void	Called just after a training iteration.
PreIteration ( ) : void	Called just before a training iteration.

Описание методов

HybridStrategy() публичный Метод

Construct a hybrid strategy with the default minimum improvement and toleration cycles.

public HybridStrategy ( ITrain altTrain ) : System
altTrain	ITrain	The alternative training strategy.
Результат	System

HybridStrategy() публичный Метод

Create a hybrid strategy.

public HybridStrategy ( ITrain altTrain, double minImprovement, int tolerateMinImprovement, int alternateCycles ) : System
altTrain	ITrain	The alternate training algorithm.
minImprovement	double	The minimum improvement to switch algorithms.
tolerateMinImprovement	int	The number of cycles to tolerate the /// minimum improvement for.
alternateCycles	int	How many cycles should the alternate /// training algorithm be used for.
Результат	System

Init() публичный Метод

Initialize this strategy.

public Init ( ITrain train ) : void
train	ITrain	The training algorithm.
Результат	void

PostIteration() публичный Метод

Called just after a training iteration.

public PostIteration ( ) : void
Результат	void

PreIteration() публичный Метод

Called just before a training iteration.

public PreIteration ( ) : void
Результат	void