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

This reset strategy will reset the weights if the neural network fails to improve by the specified amount over a number of cycles.

Наследование: IStrategy

Показать файл Открыть проект

Открытые методы

Метод	Описание
Init ( ITrain train ) : void	Initialize this strategy.
PostIteration ( ) : void	Called just after a training iteration.
PreIteration ( ) : void	Called just before a training iteration.
RequiredImprovementStrategy ( double required, double threshold, int cycles ) : System	Construct a reset strategy. The error rate must fall below the required rate in the specified number of cycles, or the neural network will be reset to random weights and bias values.
RequiredImprovementStrategy ( double required, int cycles ) : System	Construct a reset strategy. The error rate must fall below the required rate in the specified number of cycles, or the neural network will be reset to random weights and bias values.
RequiredImprovementStrategy ( int cycles ) : System	Reset if there is not at least a 1% improvement for 5 cycles. Don't reset if below 10%.

Описание методов

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

RequiredImprovementStrategy() публичный Метод

Construct a reset strategy. The error rate must fall below the required rate in the specified number of cycles, or the neural network will be reset to random weights and bias values.

public RequiredImprovementStrategy ( double required, double threshold, int cycles ) : System
required	double	The required error rate.
threshold	double	The accepted threshold, don't reset if error is below this.
cycles	int	The number of cycles to reach that rate.
Результат	System

RequiredImprovementStrategy() публичный Метод

Construct a reset strategy. The error rate must fall below the required rate in the specified number of cycles, or the neural network will be reset to random weights and bias values.

public RequiredImprovementStrategy ( double required, int cycles ) : System
required	double	The required error rate.
cycles	int	The number of cycles to reach that rate.
Результат	System

RequiredImprovementStrategy() публичный Метод

Reset if there is not at least a 1% improvement for 5 cycles. Don't reset if below 10%.

public RequiredImprovementStrategy ( int cycles ) : System
cycles	int	How many cycles to tolerate.
Результат	System