C# Класс Encog.Neural.Networks.Structure.NetworkCODEC

This class will extract the "long term memory" of a neural network, that is the weights and bias values into an array. This array can be used to view the neural network as a linear array of doubles. These values can then be modified and copied back into the neural network. This is very useful for simulated annealing, as well as genetic algorithms.

Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод	Описание
ArrayToNetwork ( double array, IMLMethod network ) : void	Use an array to populate the memory of the neural network.
Equals ( BasicNetwork network1, BasicNetwork network2 ) : bool	Determine if the two neural networks are equal. Uses exact precision required by Arrays.equals.
Equals ( BasicNetwork network1, BasicNetwork network2, int precision ) : bool	Determine if the two neural networks are equal.
NetworkSize ( IMLMethod network ) : int	Determine the network size.
NetworkToArray ( IMLMethod network ) : double[]	Convert to an array. This is used with some training algorithms that require that the "memory" of the neuron(the weight and bias values) be expressed as a linear array.

Описание методов

ArrayToNetwork() публичный статический Метод

Use an array to populate the memory of the neural network.

public static ArrayToNetwork ( double array, IMLMethod network ) : void
array	double	An array of doubles.
network	IMLMethod	The network to encode.
Результат	void

Equals() публичный статический Метод

Determine if the two neural networks are equal. Uses exact precision required by Arrays.equals.

public static Equals ( BasicNetwork network1, BasicNetwork network2 ) : bool
network1	BasicNetwork	The first network.
network2	BasicNetwork	The second network.
Результат	bool

Equals() публичный статический Метод

Determine if the two neural networks are equal.

public static Equals ( BasicNetwork network1, BasicNetwork network2, int precision ) : bool
network1	BasicNetwork	The first network.
network2	BasicNetwork	The second network.
precision	int	How many decimal places to check.
Результат	bool

NetworkSize() публичный статический Метод

Determine the network size.

public static NetworkSize ( IMLMethod network ) : int
network	IMLMethod	The network.
Результат	int

NetworkToArray() публичный статический Метод

Convert to an array. This is used with some training algorithms that require that the "memory" of the neuron(the weight and bias values) be expressed as a linear array.

public static NetworkToArray ( IMLMethod network ) : double[]
network	IMLMethod	The network to encode.
Результат	double[]