Uses of Class
org.deeplearning4j.nn.conf.distribution.Distribution

Packages that use Distribution

Package	Description
org.deeplearning4j.nn.conf
org.deeplearning4j.nn.conf.distribution
org.deeplearning4j.nn.conf.distribution.serde
org.deeplearning4j.nn.conf.layers
org.deeplearning4j.nn.conf.weightnoise
org.deeplearning4j.nn.transferlearning

Uses of Distribution in org.deeplearning4j.nn.conf

Fields in org.deeplearning4j.nn.conf declared as Distribution

Modifier and Type	Field and Description
protected Distribution	NeuralNetConfiguration.Builder.dist

Methods in org.deeplearning4j.nn.conf with parameters of type Distribution

Modifier and Type	Method and Description
NeuralNetConfiguration.Builder	NeuralNetConfiguration.Builder.dist(Distribution dist) Distribution to sample initial weights from.
NeuralNetConfiguration.Builder	NeuralNetConfiguration.Builder.weightInit(Distribution distribution) Set weight initialization scheme to random sampling via the specified distribution.

Uses of Distribution in org.deeplearning4j.nn.conf.distribution

Subclasses of Distribution in org.deeplearning4j.nn.conf.distribution

Modifier and Type	Class and Description
class	BinomialDistribution A binomial distribution, with 2 parameters: number of trials, and probability of success
class	ConstantDistribution Constant distribution: a "distribution" where all values are set to the specified constant
class	GaussianDistribution Deprecated. Use NormalDistribution which is identical to this implementation
class	LogNormalDistribution A log-normal distribution, with two parameters: mean and standard deviation.
class	NormalDistribution A normal (Gaussian) distribution, with two parameters: mean and standard deviation
class	OrthogonalDistribution Orthogonal distribution, with gain parameter. See http://arxiv.org/abs/1312.6120 for details
class	TruncatedNormalDistribution A truncated normal distribution, with 2 parameters: mean and standard deviation This distribution is a standard normal/Gaussian distribtion, however values are "truncated" in the sense that any values that fall outside the range [mean - 2 * stdev, mean + 2 * stdev] are re-sampled.
class	UniformDistribution A uniform distribution, with two parameters: lower and upper - i.e., U(lower,upper)

Methods in org.deeplearning4j.nn.conf.distribution that return Distribution

Modifier and Type	Method and Description
Distribution	Distribution.clone()

Methods in org.deeplearning4j.nn.conf.distribution with parameters of type Distribution

Modifier and Type	Method and Description
static Distribution	Distributions.createDistribution(Distribution dist)

Uses of Distribution in org.deeplearning4j.nn.conf.distribution.serde

Subclasses of Distribution in org.deeplearning4j.nn.conf.distribution.serde

Modifier and Type	Class and Description
class	LegacyDistributionHelper A dummy helper "distribution" for deserializing distributions in legacy/different JSON format.

Methods in org.deeplearning4j.nn.conf.distribution.serde that return Distribution

Modifier and Type	Method and Description
Distribution	LegacyDistributionDeserializer.deserialize(org.nd4j.shade.jackson.core.JsonParser jp, org.nd4j.shade.jackson.databind.DeserializationContext deserializationContext)

Uses of Distribution in org.deeplearning4j.nn.conf.layers

Fields in org.deeplearning4j.nn.conf.layers declared as Distribution

Modifier and Type	Field and Description
protected Distribution	BaseLayer.dist
protected Distribution	BaseLayer.Builder.dist
protected Distribution	BaseRecurrentLayer.distRecurrent
protected Distribution	BaseRecurrentLayer.Builder.distRecurrent

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

Modifier and Type	Method and Description
T	BaseLayer.Builder.dist(Distribution dist) Distribution to sample initial weights from.
static void	LayerValidation.generalValidation(String layerName, Layer layer, IDropout iDropout, double l2, double l2Bias, double l1, double l1Bias, Distribution dist, List<LayerConstraint> allParamConstraints, List<LayerConstraint> weightConstraints, List<LayerConstraint> biasConstraints)
static void	LayerValidation.generalValidation(String layerName, Layer layer, IDropout iDropOut, Double l2, Double l2Bias, Double l1, Double l1Bias, Distribution dist, List<LayerConstraint> allParamConstraints, List<LayerConstraint> weightConstraints, List<LayerConstraint> biasConstraints)
T	BaseLayer.Builder.weightInit(Distribution distribution) Set weight initialization scheme to random sampling via the specified distribution.
T	BaseRecurrentLayer.Builder.weightInitRecurrent(Distribution dist) Set the weight initialization for the recurrent weights, based on the specified distribution.

Uses of Distribution in org.deeplearning4j.nn.conf.weightnoise

Constructors in org.deeplearning4j.nn.conf.weightnoise with parameters of type Distribution

Constructor and Description
WeightNoise(Distribution distribution)
WeightNoise(Distribution distribution, boolean additive)
WeightNoise(Distribution distribution, boolean applyToBias, boolean additive)

Uses of Distribution in org.deeplearning4j.nn.transferlearning

Fields in org.deeplearning4j.nn.transferlearning declared as Distribution

Modifier and Type	Field and Description
protected Distribution	FineTuneConfiguration.dist

Methods in org.deeplearning4j.nn.transferlearning with parameters of type Distribution

Modifier and Type	Method and Description
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.dist(Distribution dist) Distribution to sample initial weights from.
TransferLearning.Builder	TransferLearning.Builder.nInReplace(int layerNum, int nIn, WeightInit scheme, Distribution dist) Modify the architecture of a vertex layer by changing nIn of the specified layer. Note that only the specified layer will be modified - all other layers will not be changed by this call.
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.nInReplace(String layerName, int nIn, WeightInit scheme, Distribution dist) Modify the architecture of a vertex layer by changing nIn of the specified layer. Note that only the specified layer will be modified - all other layers will not be changed by this call.
TransferLearning.Builder	TransferLearning.Builder.nOutReplace(int layerNum, int nOut, Distribution dist) Modify the architecture of a layer by changing nOut Note this will also affect the layer that follows the layer specified, unless it is the output layer
TransferLearning.Builder	TransferLearning.Builder.nOutReplace(int layerNum, int nOut, Distribution dist, Distribution distNext) Modify the architecture of a layer by changing nOut Note this will also affect the layer that follows the layer specified, unless it is the output layer Can specify different weight init schemes for the specified layer and the layer that follows it.
TransferLearning.Builder	TransferLearning.Builder.nOutReplace(int layerNum, int nOut, Distribution dist, WeightInit schemeNext) Modify the architecture of a layer by changing nOut Note this will also affect the layer that follows the layer specified, unless it is the output layer Can specify different weight init schemes for the specified layer and the layer that follows it.
TransferLearning.Builder	TransferLearning.Builder.nOutReplace(int layerNum, int nOut, WeightInit scheme, Distribution distNext) Modify the architecture of a layer by changing nOut Note this will also affect the layer that follows the layer specified, unless it is the output layer Can specify different weight init schemes for the specified layer and the layer that follows it.
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.nOutReplace(String layerName, int nOut, Distribution dist) Modify the architecture of a vertex layer by changing nOut Note this will also affect the vertex layer that follows the layer specified, unless it is the output layer Currently does not support modifying nOut of layers that feed into non-layer vertices like merge, subset etc To modify nOut for such vertices use remove vertex, followed by add vertex Can specify different weight init schemes for the specified layer and the layer that follows it.
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.nOutReplace(String layerName, int nOut, Distribution dist, Distribution distNext) Modified nOut of specified layer.
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.nOutReplace(String layerName, int nOut, Distribution dist, WeightInit scheme)
TransferLearning.GraphBuilder	TransferLearning.GraphBuilder.nOutReplace(String layerName, int nOut, WeightInit scheme, Distribution dist)
FineTuneConfiguration.Builder	FineTuneConfiguration.Builder.weightInit(Distribution distribution) Set weight initialization scheme to random sampling via the specified distribution. Equivalent to: .weightInit(WeightInit.DISTRIBUTION).dist(distribution)