SharedDispersion

latent.layers.SharedDispersion

Layer to get shared dispersion estimates per gene.

__init__(self, units, name=None, activation='clipped_exp', initializer='glorot_normal') special

Parameters:

Name	Type	Description	Default
units	int	Positive integer, dimensionality of the output space.	required
name	str	String indicating the name of the layer.	None
activation	Union[str, Callable]	Activation function to use.	'clipped_exp'
initializer	Union[str, Callable]	Initializer for the kernel weights matrix.	'glorot_normal'