Uses of Interface
org.deeplearning4j.nn.conf.layers.variational.ReconstructionDistribution

Packages that use ReconstructionDistribution

Package	Description
org.deeplearning4j.nn.conf.layers.variational
org.deeplearning4j.nn.conf.serde.legacyformat
org.deeplearning4j.nn.layers.variational

Uses of ReconstructionDistribution in org.deeplearning4j.nn.conf.layers.variational

Classes in org.deeplearning4j.nn.conf.layers.variational that implement ReconstructionDistribution

Modifier and Type	Class and Description
class	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.
class	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.
class	ExponentialReconstructionDistribution Exponential reconstruction distribution. Supports data in range [0,infinity)
class	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.
class	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.

Methods in org.deeplearning4j.nn.conf.layers.variational with parameters of type ReconstructionDistribution

Modifier and Type	Method and Description
CompositeReconstructionDistribution.Builder	CompositeReconstructionDistribution.Builder.addDistribution(int distributionSize, ReconstructionDistribution distribution) Add another distribution to the composite distribution.
VariationalAutoencoder.Builder	VariationalAutoencoder.Builder.reconstructionDistribution(ReconstructionDistribution distribution) The reconstruction distribution for the data given the hidden state - i.e., P(data|Z). This should be selected carefully based on the type of data being modelled.

Constructors in org.deeplearning4j.nn.conf.layers.variational with parameters of type ReconstructionDistribution

Constructor and Description
CompositeReconstructionDistribution(int[] distributionSizes, ReconstructionDistribution[] reconstructionDistributions, int totalSize)

Uses of ReconstructionDistribution in org.deeplearning4j.nn.conf.serde.legacyformat

Method parameters in org.deeplearning4j.nn.conf.serde.legacyformat with type arguments of type ReconstructionDistribution

Modifier and Type	Method and Description
static void	LegacyReconstructionDistributionDeserializer.registerLegacyClassDefaultName(Class<? extends ReconstructionDistribution> clazz)
static void	LegacyReconstructionDistributionDeserializer.registerLegacyClassSpecifiedName(String name, Class<? extends ReconstructionDistribution> clazz)

Uses of ReconstructionDistribution in org.deeplearning4j.nn.layers.variational

Fields in org.deeplearning4j.nn.layers.variational declared as ReconstructionDistribution

Modifier and Type	Field and Description
protected ReconstructionDistribution	VariationalAutoencoder.reconstructionDistribution