C# 클래스 Encog.Neural.Networks.Training.Propagation.Quick.QuickPropagation

QPROP is an efficient training method that is based on Newton's Method. QPROP was introduced in a paper: An Empirical Study of Learning Speed in Back-Propagation Networks" (Scott E. Fahlman, 1988) http://www.heatonresearch.com/wiki/Quickprop
상속: Propagation, ILearningRate
파일 보기 프로젝트 열기: encog/encog-silverlight-core

공개 메소드들

메소드 설명
IsValidResume ( TrainingContinuation state ) : bool

Determine if the specified continuation object is valid to resume with.

Pause ( ) : TrainingContinuation

Pause the training.

QuickPropagation ( IContainsFlat network, IMLDataSet training ) : System

Construct a QPROP trainer for flat networks. Uses a learning rate of 2.

QuickPropagation ( IContainsFlat network, IMLDataSet training, double learnRate ) : System

Construct a QPROP trainer for flat networks.

Resume ( TrainingContinuation state ) : void

Resume training.

메소드 상세

IsValidResume() 공개 메소드

Determine if the specified continuation object is valid to resume with.
public IsValidResume ( TrainingContinuation state ) : bool
state TrainingContinuation The continuation object to check.
리턴 bool

Pause() 공개 메소드

Pause the training.
public Pause ( ) : TrainingContinuation
리턴 TrainingContinuation

QuickPropagation() 공개 메소드

Construct a QPROP trainer for flat networks. Uses a learning rate of 2.
public QuickPropagation ( IContainsFlat network, IMLDataSet training ) : System
network IContainsFlat The network to train.
training IMLDataSet The training data.
리턴 System

QuickPropagation() 공개 메소드

Construct a QPROP trainer for flat networks.
public QuickPropagation ( IContainsFlat network, IMLDataSet training, double learnRate ) : System
network IContainsFlat The network to train.
training IMLDataSet The training data.
learnRate double The learning rate. 2 is a good suggestion as /// a learning rate to start with. If it fails to converge, /// then drop it. Just like backprop, except QPROP can /// take higher learning rates.
리턴 System

Resume() 공개 메소드

Resume training.
public Resume ( TrainingContinuation state ) : void
state TrainingContinuation The training state to return to.
리턴 void