C# Класс Encog.Neural.Networks.Pattern.SOMPattern

A self organizing map is a neural network pattern with an input and output layer. There is no hidden layer. The winning neuron, which is that neuron with the higest output is the winner, this winning neuron is often used to classify the input into a group.

Наследование: INeuralNetworkPattern

Показать файл Открыть проект

Открытые методы

Метод	Описание
AddHiddenLayer ( int count ) : void	Add a hidden layer. SOM networks do not have hidden layers, so this will throw an error.
Clear ( ) : void	Does nothing, no optinal hidden layers to clear, only the ONE predefined hidden layer.
Generate ( ) : BasicNetwork	Generate the RSOM network.

Описание методов

AddHiddenLayer() публичный Метод

Add a hidden layer. SOM networks do not have hidden layers, so this will throw an error.

public AddHiddenLayer ( int count ) : void
count	int	The number of hidden neurons.
Результат	void

Clear() публичный Метод

Does nothing, no optinal hidden layers to clear, only the ONE predefined hidden layer.

public Clear ( ) : void
Результат	void

Generate() публичный Метод

Generate the RSOM network.

public Generate ( ) : BasicNetwork
Результат	BasicNetwork