C# 클래스 Encog.Neural.SOM.Training.Neighborhood.BasicTrainSOM

상속: BasicTraining, ILearningRate
파일 보기 프로젝트 열기: encog/encog-silverlight-core 1 사용 예제들

공개 메소드들

메소드 설명
AutoDecay ( ) : void

Should be called each iteration if autodecay is desired.

BasicTrainSOM ( SOMNetwork network, double learningRate, IMLDataSet training, INeighborhoodFunction neighborhood ) : System

Create an instance of competitive training.

Decay ( double d ) : void

Called to decay the learning rate and radius by the specified amount.

Decay ( double decayRate, double decayRadius ) : void

Decay the learning rate and radius by the specified amount.

Iteration ( ) : void

Perform one training iteration.

Pause ( ) : TrainingContinuation

Resume ( TrainingContinuation state ) : void

SetAutoDecay ( int plannedIterations, double startRate, double endRate, double startRadius, double endRadius ) : void

Setup autodecay. This will decrease the radius and learning rate from the start values to the end values.

SetParams ( double rate, double radius ) : void

Set the learning rate and radius.

ToString ( ) : String

TrainPattern ( IMLData pattern ) : void

Train the specified pattern. Find a winning neuron and adjust all neurons according to the neighborhood function.

비공개 메소드들

메소드 설명
ApplyCorrection ( ) : void

Loop over the synapses to be trained and apply any corrections that were determined by this training iteration.

CopyInputPattern ( Matrix matrix, int outputNeuron, IMLData input ) : void

Copy the specified input pattern to the weight matrix. This causes an output neuron to learn this pattern "exactly". This is useful when a winner is to be forced.

DetermineNewWeight ( double weight, double input, int currentNeuron, int bmu ) : double

Determine the weight adjustment for a single neuron during a training iteration.

ForceWinners ( Matrix matrix, int won, IMLData leastRepresented ) : bool

Force any neurons that did not win to off-load patterns from overworked neurons.

Train ( int bmu, Matrix matrix, IMLData input ) : void

Train for the specified synapse and BMU.

TrainPattern ( Matrix matrix, IMLData input, int current, int bmu ) : void

Train for the specified pattern.

메소드 상세

AutoDecay() 공개 메소드

Should be called each iteration if autodecay is desired.
public AutoDecay ( ) : void
리턴 void

BasicTrainSOM() 공개 메소드

Create an instance of competitive training.
public BasicTrainSOM ( SOMNetwork network, double learningRate, IMLDataSet training, INeighborhoodFunction neighborhood ) : System
network Encog.Neural.SOM.SOMNetwork The network to train.
learningRate double The learning rate, how much to apply per iteration.
training IMLDataSet The training set (unsupervised).
neighborhood INeighborhoodFunction The neighborhood function to use.
리턴 System

Decay() 공개 메소드

Called to decay the learning rate and radius by the specified amount.
public Decay ( double d ) : void
d double The percent to decay by.
리턴 void

Decay() 공개 메소드

Decay the learning rate and radius by the specified amount.
public Decay ( double decayRate, double decayRadius ) : void
decayRate double The percent to decay the learning rate by.
decayRadius double The percent to decay the radius by.
리턴 void

Iteration() 공개 최종 메소드

Perform one training iteration.
public final Iteration ( ) : void
리턴 void

Pause() 공개 최종 메소드

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

Resume() 공개 메소드

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

SetAutoDecay() 공개 메소드

Setup autodecay. This will decrease the radius and learning rate from the start values to the end values.
public SetAutoDecay ( int plannedIterations, double startRate, double endRate, double startRadius, double endRadius ) : void
plannedIterations int
startRate double The starting learning rate.
endRate double The ending learning rate.
startRadius double The starting radius.
endRadius double The ending radius.
리턴 void

SetParams() 공개 메소드

Set the learning rate and radius.
public SetParams ( double rate, double radius ) : void
rate double The new learning rate.
radius double The new radius.
리턴 void

ToString() 공개 최종 메소드

public final ToString ( ) : String
리턴 String

TrainPattern() 공개 메소드

Train the specified pattern. Find a winning neuron and adjust all neurons according to the neighborhood function.
public TrainPattern ( IMLData pattern ) : void
pattern IMLData The pattern to train.
리턴 void