C# Класс Encog.Neural.Networks.Prune.PruneIncremental

This class is used to help determine the optimal configuration for the hidden layers of a neural network. It can accept a pattern, which specifies the type of neural network to create, and a list of the maximum and minimum hidden layer neurons. It will then attempt to train the neural network at all configurations and see which hidden neuron counts work the best.

Наследование: Encog.Engine.Concurrency.Job.ConcurrentJob

Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод	Описание
AddHiddenLayer ( int min, int max ) : void
LoadWorkload ( ) : int	Load all workloads, calculate how many networks we will examine.
NetworkToString ( BasicNetwork network ) : String	Format the network as a human readable string that lists the hidden layers.
PerformJobUnit ( JobUnitContext context ) : void	Evaluate one network.
Process ( ) : void	Begin process and find a good network.
PruneIncremental ( INeuralDataSet training, INeuralNetworkPattern pattern, int iterations, IStatusReportable report ) : log4net
RequestNextTask ( ) : Object	Request the next task, the next network to try.

Приватные методы

Метод	Описание
GenerateNetwork ( ) : BasicNetwork
IncreaseHiddenCounts ( ) : bool

Описание методов

AddHiddenLayer() публичный Метод

public AddHiddenLayer ( int min, int max ) : void
min	int
max	int
Результат	void

LoadWorkload() публичный Метод

Load all workloads, calculate how many networks we will examine.

public LoadWorkload ( ) : int
Результат	int

NetworkToString() публичный статический Метод

Format the network as a human readable string that lists the hidden layers.

public static NetworkToString ( BasicNetwork network ) : String
network	BasicNetwork	The network to format.
Результат	String

PerformJobUnit() публичный Метод

Evaluate one network.

public PerformJobUnit ( JobUnitContext context ) : void
context	Encog.Engine.Concurrency.Job.JobUnitContext	The job context.
Результат	void

Process() публичный Метод

Begin process and find a good network.

public Process ( ) : void
Результат	void

PruneIncremental() публичный Метод

public PruneIncremental ( INeuralDataSet training, INeuralNetworkPattern pattern, int iterations, IStatusReportable report ) : log4net
training	INeuralDataSet
pattern	INeuralNetworkPattern
iterations	int
report	IStatusReportable
Результат	log4net

RequestNextTask() публичный Метод

Request the next task, the next network to try.

public RequestNextTask ( ) : Object
Результат	Object