C# Class Encog.Neural.Prune.PruneIncremental

Inheritance: Encog.Util.Concurrency.Job.ConcurrentJob
Afficher le fichier Open project: encog/encog-silverlight-core Class Usage Examples

Méthodes publiques

Méthode Description
AddHiddenLayer ( int min, int max ) : void

Add a hidden layer's min and max. Call this once per hidden layer. Specify a zero min if it is possible to remove this hidden layer.
Init ( ) : void

Init for prune.
LoadWorkload ( ) : int

Get the next workload. This is the number of hidden neurons. This is the total amount of work to be processed.
NetworkToString ( BasicNetwork network ) : String

Format the network as a human readable string that lists the hidden layers.
PerformJobUnit ( JobUnitContext context ) : void

Perform an individual job unit, which is a single network to train and evaluate.
Process ( ) : void

Begin the prune process.
PruneIncremental ( IMLDataSet training, INeuralNetworkPattern pattern, int iterations, int weightTries, int numTopResults, IStatusReportable report ) : System

Construct an object to determine the optimal number of hidden layers and neurons for the specified training data and pattern.
RequestNextTask ( ) : Object

Request the next task. This is the next network to attempt to train.

Private Methods

Méthode Description
GenerateNetwork ( ) : BasicNetwork

Generate a network according to the current hidden layer counts.
IncreaseHiddenCounts ( ) : bool

Increase the hidden layer counts according to the hidden layer parameters. Increase the first hidden layer count by one, if it is maxed out, then set it to zero and increase the next hidden layer.
UpdateBest ( BasicNetwork network, double error ) : void

Method Details

AddHiddenLayer() public méthode

Add a hidden layer's min and max. Call this once per hidden layer. Specify a zero min if it is possible to remove this hidden layer.
public AddHiddenLayer ( int min, int max ) : void
min int The minimum number of neurons for this layer.
max int The maximum number of neurons for this layer.
Résultat void

Init() public méthode

Init for prune.
public Init ( ) : void
Résultat void

LoadWorkload() public final méthode

Get the next workload. This is the number of hidden neurons. This is the total amount of work to be processed.
public final LoadWorkload ( ) : int
Résultat int

NetworkToString() public static méthode

Format the network as a human readable string that lists the hidden layers.
public static NetworkToString ( BasicNetwork network ) : String
network Encog.Neural.Networks.BasicNetwork The network to format.
Résultat String

PerformJobUnit() public final méthode

Perform an individual job unit, which is a single network to train and evaluate.
public final PerformJobUnit ( JobUnitContext context ) : void
context Encog.Util.Concurrency.Job.JobUnitContext Contains information about the job unit.
Résultat void

Process() public final méthode

Begin the prune process.
public final Process ( ) : void
Résultat void

PruneIncremental() public méthode

Construct an object to determine the optimal number of hidden layers and neurons for the specified training data and pattern.
public PruneIncremental ( IMLDataSet training, INeuralNetworkPattern pattern, int iterations, int weightTries, int numTopResults, IStatusReportable report ) : System
training IMLDataSet The training data to use.
pattern INeuralNetworkPattern The network pattern to use to solve this data.
iterations int How many iterations to try per network.
weightTries int The number of random weights to use.
numTopResults int
report IStatusReportable Object used to report status to.
Résultat System

RequestNextTask() public final méthode

Request the next task. This is the next network to attempt to train.
public final RequestNextTask ( ) : Object
Résultat Object