Modifier and Type | Method and Description |
---|---|
T |
BaseNetworkSpace.Builder.idropOut(IDropout idropOut) |
Modifier and Type | Method and Description |
---|---|
T |
BaseNetworkSpace.Builder.idropOut(ParameterSpace<IDropout> idropOut) |
Modifier and Type | Method and Description |
---|---|
IDropout |
AlphaDropoutSpace.getValue(double[] parameterValues) |
IDropout |
DropoutSpace.getValue(double[] parameterValues) |
IDropout |
GaussianDropoutSpace.getValue(double[] parameterValues) |
IDropout |
GaussianNoiseSpace.getValue(double[] parameterValues) |
Modifier and Type | Field and Description |
---|---|
protected ParameterSpace<IDropout> |
LayerSpace.dropOut |
protected ParameterSpace<IDropout> |
LayerSpace.Builder.dropOut |
Modifier and Type | Method and Description |
---|---|
DropoutLayerSpace.Builder |
DropoutLayerSpace.Builder.iDropOut(ParameterSpace<IDropout> dropout) |
T |
LayerSpace.Builder.iDropOut(ParameterSpace<IDropout> dropOut) |
Modifier and Type | Field and Description |
---|---|
protected IDropout |
NeuralNetConfiguration.Builder.idropOut |
Modifier and Type | Method and Description |
---|---|
NeuralNetConfiguration.Builder |
NeuralNetConfiguration.Builder.dropOut(IDropout dropout)
Set the dropout for all layers in this network
Note: values set by this method will be applied to all applicable layers in the network, unless a different value is explicitly set on a given layer. |
Modifier and Type | Class and Description |
---|---|
class |
AlphaDropout
AlphaDropout is a dropout technique proposed by Klaumbauer et al. 2017 - Self-Normalizing Neural Networks
https://arxiv.org/abs/1706.02515
This dropout technique was designed specifically for self-normalizing neural networks - i.e., networks using ActivationSELU / Activation.SELU
activation function, combined with the N(0,stdev=1/sqrt(fanIn)) "SNN" weight initialization,
WeightInit.NORMAL In conjuction with the aforementioned activation function and weight initialization, AlphaDropout attempts to keep both the mean and variance of the post-dropout activations to the same (in expectation) as before alpha dropout was applied. |
class |
Dropout
Implements standard (inverted) dropout.
|
class |
GaussianDropout
Gaussian dropout.
|
class |
GaussianNoise
Applies additive, mean-zero Gaussian noise to the input - i.e., x = x + N(0,stddev).
|
class |
SpatialDropout
Spatial dropout: can only be applied to 3D (time series), 4D (convolutional 2D) or 5D (convolutional 3D) activations.
|
Modifier and Type | Method and Description |
---|---|
IDropout |
GaussianNoise.clone() |
IDropout |
IDropout.clone() |
IDropout |
SpatialDropout.clone() |
Modifier and Type | Field and Description |
---|---|
protected IDropout |
Layer.iDropout |
protected IDropout |
Layer.Builder.iDropout |
Modifier and Type | Method and Description |
---|---|
T |
Layer.Builder.dropOut(IDropout dropout)
Set the dropout for all layers in this network
|
static void |
LayerValidation.generalValidation(String layerName,
Layer layer,
IDropout iDropout,
List<Regularization> regularization,
List<Regularization> regularizationBias,
List<LayerConstraint> allParamConstraints,
List<LayerConstraint> weightConstraints,
List<LayerConstraint> biasConstraints) |
Constructor and Description |
---|
Builder(IDropout dropout) |
DropoutLayer(IDropout dropout) |
Modifier and Type | Field and Description |
---|---|
protected Optional<IDropout> |
FineTuneConfiguration.dropout |
Modifier and Type | Method and Description |
---|---|
FineTuneConfiguration.Builder |
FineTuneConfiguration.Builder.dropout(IDropout dropout)
Set the dropout
|
Copyright © 2020. All rights reserved.