C# Class SuperNeuro.Layers.Activations.Tanh

Hyperbolic tangent activation. Tanh squashes a real-valued number to the range [-1, 1]. It’s non-linear. But unlike Sigmoid, its output is zero-centered. Therefore, in practice the tanh non-linearity is always preferred to the sigmoid nonlinearity.

Inheritance: BaseLayer

Afficher le fichier Open project: tech-quantum/SuperchargedArray Class Usage Examples

Méthodes publiques

Méthode	Description
Backward ( SuperArray outputgrad ) : void	Calculate the gradient of this layer function
Forward ( SuperArray x ) : void	Forwards the inputs and compute the output
Tanh ( ) : SuperchargedArray	Initializes a new instance of the Tanh class.

Method Details

Backward() public méthode

Calculate the gradient of this layer function

public Backward ( SuperArray outputgrad ) : void
outputgrad	SuperArray	The calculated output grad from previous layer.
Résultat	void

Forward() public méthode

Forwards the inputs and compute the output

public Forward ( SuperArray x ) : void
x	SuperArray	The input SuperArray for this layer.
Résultat	void

Tanh() public méthode

Initializes a new instance of the Tanh class.

public Tanh ( ) : SuperchargedArray
Résultat	SuperchargedArray