C# 클래스 NNX.Core.Training.SimpleGradientTrainer

A SimpleGradientTrainer is an on-line gradient descent trainer that applies backpropagation (with a few adjustments) NumEpochs times. Next input/target pair is selected randomly from the training set.

상속: BaseTrainer

파일 보기 프로젝트 열기: ikhramts/NNX 1 사용 예제들

공개 메소드들

메소드	설명
AdjustWeights ( INeuralNetwork nn, double weightGradients, double prevWeightGradients ) : void
GetValidationSetFraction ( ) : double
Train ( IList trainingSet, IList validationSet, IRandomGenerator rand, INeuralNetwork nn ) : void
Validate ( ) : void

메소드 상세

AdjustWeights() 공개 메소드

public AdjustWeights ( INeuralNetwork nn, double weightGradients, double prevWeightGradients ) : void
nn	INeuralNetwork
weightGradients	double
prevWeightGradients	double
리턴	void

GetValidationSetFraction() 공개 메소드

public GetValidationSetFraction ( ) : double
리턴	double

Train() 공개 메소드

public Train ( IList trainingSet, IList validationSet, IRandomGenerator rand, INeuralNetwork nn ) : void
trainingSet	IList
validationSet	IList
rand	IRandomGenerator
nn	INeuralNetwork
리턴	void

Validate() 공개 메소드

public Validate ( ) : void
리턴	void