C# 클래스 Accord.Neuro.Learning.DeepBeliefNetworkLearning

Deep Belief Network learning algorithm.

상속: IUnsupervisedLearning

파일 보기 프로젝트 열기: accord-net/framework 1 사용 예제들

공개 메소드들

메소드	설명
ComputeError ( double inputs ) : double	Computes the reconstruction error for a given set of input values.
DeepBeliefNetworkLearning ( DeepBeliefNetwork network ) : System	Creates a new DeepBeliefNetworkLearning algorithm.
GetLayerAlgorithm ( int layerIndex ) : IUnsupervisedLearning	Gets the unsupervised learning algorithm allocated for the given layer.
GetLayerInput ( double input ) : double[][]	Gets the learning data needed to train the currently selected layer. The return of this function should then be passed to RunEpoch(double[][]) to actually run a learning epoch.
GetLayerInput ( double batches ) : double[][][]	Gets the learning data needed to train the currently selected layer. The return of this function should then be passed to RunEpoch(double[][]) to actually run a learning epoch.
Run ( double input ) : double	Runs a single learning iteration.
RunEpoch ( double input ) : double	Runs a single batch epoch of the learning algorithm.

비공개 메소드들

메소드	설명
createAlgorithms ( ) : void

메소드 상세

ComputeError() 공개 메소드

Computes the reconstruction error for a given set of input values.

public ComputeError ( double inputs ) : double
inputs	double	The input values.
리턴	double

DeepBeliefNetworkLearning() 공개 메소드

Creates a new DeepBeliefNetworkLearning algorithm.

public DeepBeliefNetworkLearning ( DeepBeliefNetwork network ) : System
network	Accord.Neuro.Networks.DeepBeliefNetwork	The network to be trained.
리턴	System

GetLayerAlgorithm() 공개 메소드

Gets the unsupervised learning algorithm allocated for the given layer.

public GetLayerAlgorithm ( int layerIndex ) : IUnsupervisedLearning
layerIndex	int	The index of the layer to get the algorithm for.
리턴	IUnsupervisedLearning

GetLayerInput() 공개 메소드

Gets the learning data needed to train the currently selected layer. The return of this function should then be passed to RunEpoch(double[][]) to actually run a learning epoch.

public GetLayerInput ( double input ) : double[][]
input	double	The batch of input data.
리턴	double[][]

GetLayerInput() 공개 메소드

Gets the learning data needed to train the currently selected layer. The return of this function should then be passed to RunEpoch(double[][]) to actually run a learning epoch.

public GetLayerInput ( double batches ) : double[][][]
batches	double	The mini-batches of input data.
리턴	double[][][]

Run() 공개 메소드

Runs a single learning iteration.

public Run ( double input ) : double
input	double	A single input vector.
리턴	double

RunEpoch() 공개 메소드

Runs a single batch epoch of the learning algorithm.

public RunEpoch ( double input ) : double
input	double	Array of input vectors.
리턴	double