C# Class Encog.Neural.Networks.Training.Anneal.NeuralSimulatedAnnealing

This class implements a simulated annealing training algorithm for neural networks. It is based on the generic SimulatedAnnealing class. It is used in the same manner as any other training class that implements the Train interface. There are essentially two ways you can make use of this class. Either way, you will need a score object. The score object tells the simulated annealing algorithm how well suited a neural network is. If you would like to use simulated annealing with a training set you should make use TrainingSetScore class. This score object uses a training set to score your neural network. If you would like to be more abstract, and not use a training set, you can create your own implementation of the CalculateScore method. This class can then score the networks any way that you like.

Inheritance: Encog.ML.Train.BasicTraining

Exibir arquivo Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method	Description
Iteration ( ) : void	Perform one iteration of simulated annealing.
NeuralSimulatedAnnealing ( BasicNetwork network, ICalculateScore calculateScore, double startTemp, double stopTemp, int cycles ) : Encog.ML	Construct a simulated annleaing trainer for a feedforward neural network.
Pause ( ) : TrainingContinuation
PutArray ( double array ) : void	Convert an array of doubles to the current best network.
Randomize ( ) : void	Randomize the weights and bias values. This function does most of the work of the class. Each call to this class will randomize the data according to the current temperature. The higher the temperature the more randomness.
Resume ( TrainingContinuation state ) : void

Method Details

Iteration() public final method

Perform one iteration of simulated annealing.

public final Iteration ( ) : void
return	void

NeuralSimulatedAnnealing() public method

Construct a simulated annleaing trainer for a feedforward neural network.

public NeuralSimulatedAnnealing ( BasicNetwork network, ICalculateScore calculateScore, double startTemp, double stopTemp, int cycles ) : Encog.ML
network	BasicNetwork	The neural network to be trained.
calculateScore	ICalculateScore	Used to calculate the score for a neural network.
startTemp	double	The starting temperature.
stopTemp	double	The ending temperature.
cycles	int	The number of cycles in a training iteration.
return	Encog.ML

Pause() public method

public Pause ( ) : TrainingContinuation
return	Encog.Neural.Networks.Training.Propagation.TrainingContinuation

PutArray() public method

Convert an array of doubles to the current best network.

public PutArray ( double array ) : void
array	double	An array.
return	void

Randomize() public method

Randomize the weights and bias values. This function does most of the work of the class. Each call to this class will randomize the data according to the current temperature. The higher the temperature the more randomness.

public Randomize ( ) : void
return	void

Resume() public method

public Resume ( TrainingContinuation state ) : void
state	Encog.Neural.Networks.Training.Propagation.TrainingContinuation
return	void