Skip to content

TopologicalEncoder

latent.modules.encoder.TopologicalEncoder

Encoder model with topological regularization loss on latent space (Moor 2019).

__init__(self, latent_dim=50, name='topological_encoder', initializer='glorot_normal', topo_weight=1.0, **kwargs) special

Parameters:

Name Type Description Default
latent_dim int

Integer indicating the number of dimensions in the latent space.

50
name str

String indicating the name of the model.

'topological_encoder'
initializer Union[str, Callable]

Initializer for the kernel weights matrix (see keras.initializers)

'glorot_normal'
topo_weight float

Float indicating the weight of the topological loss.

1.0
**kwargs

Other arguments passed on to DenseStack

{}