LeakyReLU

Parameters : layer parameters.

 alpha : float >= 0, negative slope coefficient.
Default value “0,3”.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

Activation : cluster, this cluster defines the activation function to be used in the model.

enum : enum, an enumeration specifying the type of activation (e.g., ReLU, Sigmoid, etc.). If enum is set to CustomActivation, the custom class on the right will be used as the activation function. Otherwise, the selected activation from the enum will be used with its default parameters.
 Class : object, a custom activation class instance.