Interface  Description 

ReconstructionDistribution 
The ReconstructionDistribution is used with variational autoencoders
VariationalAutoencoder
to specify the form of the distribution p(datax). 
Class  Description 

BernoulliReconstructionDistribution 
Bernoulli reconstruction distribution for variational autoencoder.
Outputs are modelled by a Bernoulli distribution  i.e., the Bernoulli distribution should be used for binary data (all values 0 or 1); the VAE models the probability of the output being 0 or 1. Consequently, the sigmoid activation function should be used to bound activations to the range of 0 to 1. 
CompositeReconstructionDistribution 
CompositeReconstructionDistribution is a reconstruction distribution built from multiple other ReconstructionDistribution
instances.
The typical use is to combine for example continuous and binary data in the same model, or to combine different distributions for continuous variables. 
CompositeReconstructionDistribution.Builder  
ExponentialReconstructionDistribution 
Exponential reconstruction distribution.
Supports data in range [0,infinity) 
GaussianReconstructionDistribution 
Gaussian reconstruction distribution for variational autoencoder.
Outputs are modelled by a Gaussian distribution, with the mean and variances (diagonal covariance matrix) for each output determined by the network forward pass. 
LossFunctionWrapper 
LossFunctionWrapper allows training of a VAE model with a standard (possibly deterministic) neural network loss function
for the reconstruction, instead of using a
ReconstructionDistribution as would normally be done with a VAE model. 
VariationalAutoencoder 
Variational Autoencoder layer

VariationalAutoencoder.Builder 