C# Класс Accord.Neuro.Networks.RestrictedBoltzmannMachine

Наследование: ActivationNetwork

Открытые методы

Метод	Описание
Compute ( double input ) : double[]	Compute output vector of the network.
CreateGaussianBernoulli ( int inputsCount, int hiddenNeurons ) : RestrictedBoltzmannMachine	Constructs a Gaussian-Bernoulli network with visible Gaussian units and hidden Bernoulli units.
GenerateInput ( double output ) : double[]	Samples an input vector from the network given an output vector.
GenerateOutput ( double input ) : double[]	Samples an output vector from the network given an input vector.
Reconstruct ( double output ) : double[]	Reconstructs a input vector for a given output.
RestrictedBoltzmannMachine ( IStochasticFunction function, int inputsCount, int hiddenNeurons ) : System	Creates a new RestrictedBoltzmannMachine.
RestrictedBoltzmannMachine ( StochasticLayer hidden, StochasticLayer visible ) : System	Creates a new RestrictedBoltzmannMachine.
RestrictedBoltzmannMachine ( int inputsCount, int hiddenNeurons ) : System	Creates a new RestrictedBoltzmannMachine.
ToActivationNetwork ( IActivationFunction function, int outputs ) : ActivationNetwork	Creates a new ActivationNetwork from this instance.
ToActivationNetwork ( int outputs ) : ActivationNetwork	Creates a new ActivationNetwork from this instance.
UpdateVisibleWeights ( ) : void	Updates the weights of the visible layer by copying the reverse of the weights in the hidden layer.

Compute output vector of the network.

public Compute ( double input ) : double[]
input	double	Input vector.
Результат	double[]

Constructs a Gaussian-Bernoulli network with visible Gaussian units and hidden Bernoulli units.

public static CreateGaussianBernoulli ( int inputsCount, int hiddenNeurons ) : RestrictedBoltzmannMachine
inputsCount	int	The number of inputs for the machine.
hiddenNeurons	int	The number of hidden neurons in the machine.
Результат	RestrictedBoltzmannMachine

Samples an input vector from the network given an output vector.

public GenerateInput ( double output ) : double[]
output	double	An output vector.
Результат	double[]

Samples an output vector from the network given an input vector.

public GenerateOutput ( double input ) : double[]
input	double	An input vector.
Результат	double[]

Reconstructs a input vector for a given output.

public Reconstruct ( double output ) : double[]
output	double	The output vector.
Результат	double[]

Creates a new RestrictedBoltzmannMachine.

public RestrictedBoltzmannMachine ( IStochasticFunction function, int inputsCount, int hiddenNeurons ) : System
function	IStochasticFunction	The activation function to use in the network neurons.
inputsCount	int	The number of inputs for the machine.
hiddenNeurons	int	The number of hidden neurons in the machine.
Результат	System

Creates a new RestrictedBoltzmannMachine.

public RestrictedBoltzmannMachine ( StochasticLayer hidden, StochasticLayer visible ) : System
hidden	Accord.Neuro.Layers.StochasticLayer	The hidden layer to be added in the machine.
visible	Accord.Neuro.Layers.StochasticLayer	The visible layer to be added in the machine.
Результат	System

Creates a new RestrictedBoltzmannMachine.

public RestrictedBoltzmannMachine ( int inputsCount, int hiddenNeurons ) : System
inputsCount	int	The number of inputs for the machine.
hiddenNeurons	int	The number of hidden neurons in the machine.
Результат	System

Creates a new ActivationNetwork from this instance.

public ToActivationNetwork ( IActivationFunction function, int outputs ) : ActivationNetwork
function	IActivationFunction	The activation function to use in the last layer.
outputs	int	The number of output neurons in the last layer.
Результат	ActivationNetwork

Creates a new ActivationNetwork from this instance.

public ToActivationNetwork ( int outputs ) : ActivationNetwork
outputs	int	The number of output neurons in the last layer.
Результат	ActivationNetwork

Updates the weights of the visible layer by copying the reverse of the weights in the hidden layer.

public UpdateVisibleWeights ( ) : void
Результат	void