C# Класс AForge.Neuro.Learning.BackPropagationLearning

Back propagation learning algorithm

The class implements back propagation learning algorithm, which is widely used for training multi-layer neural networks with continuous activation functions.

Наследование: ISupervisedLearning

Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод	Описание
BackPropagationLearning ( ActivationNetwork network ) : System	Initializes a new instance of the BackPropagationLearning class.
Run ( double input, double output ) : double	Runs learning iteration. Runs one learning iteration and updates neuron's weights.
RunEpoch ( double input, double output ) : double	Runs learning epoch. The method runs one learning epoch, by calling Run method for each vector provided in the input array.

Приватные методы

Метод	Описание
CalculateError ( double desiredOutput ) : double	Calculates error values for all neurons of the network.
CalculateUpdates ( double input ) : void	Calculate weights updates.
UpdateNetwork ( ) : void	Update network'sweights.

Описание методов

BackPropagationLearning() публичный Метод

Initializes a new instance of the BackPropagationLearning class.

public BackPropagationLearning ( ActivationNetwork network ) : System
network	ActivationNetwork	Network to teach.
Результат	System

Run() публичный Метод

Runs learning iteration.

Runs one learning iteration and updates neuron's weights.

public Run ( double input, double output ) : double
input	double	Input vector.
output	double	Desired output vector.
Результат	double

RunEpoch() публичный Метод

Runs learning epoch.

The method runs one learning epoch, by calling Run method for each vector provided in the input array.

public RunEpoch ( double input, double output ) : double
input	double	Array of input vectors.
output	double	Array of output vectors.
Результат	double