public abstract static class BaseRecurrentLayer.Builder<T extends BaseRecurrentLayer.Builder<T>> extends FeedForwardLayer.Builder<T>
Modifier and Type  Field and Description 

protected List<LayerConstraint> 
inputWeightConstraints
Set constraints to be applied to the RNN input weight parameters of this layer.

protected List<LayerConstraint> 
recurrentConstraints
Set constraints to be applied to the RNN recurrent weight parameters of this layer.

protected RNNFormat 
rnnDataFormat
Set the format of data expected by the RNN.

protected IWeightInit 
weightInitFnRecurrent
Set the weight initialization for the recurrent weights.

nIn, nOut
activationFn, biasInit, biasUpdater, gainInit, gradientNormalization, gradientNormalizationThreshold, iupdater, regularization, regularizationBias, weightInitFn, weightNoise
allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints
Constructor and Description 

Builder() 
Modifier and Type  Method and Description 

T 
constrainInputWeights(LayerConstraint... constraints)
Set constraints to be applied to the RNN input weight parameters of this layer.

T 
constrainRecurrent(LayerConstraint... constraints)
Set constraints to be applied to the RNN recurrent weight parameters of this layer.

T 
dataFormat(RNNFormat rnnDataFormat) 
T 
weightInitRecurrent(Distribution dist)
Set the weight initialization for the recurrent weights, based on the specified distribution.

T 
weightInitRecurrent(IWeightInit weightInit)
Set the weight initialization for the recurrent weights.

T 
weightInitRecurrent(WeightInit weightInit)
Set the weight initialization for the recurrent weights.

nIn, nIn, nOut, nOut, units
activation, activation, biasInit, biasUpdater, dist, gainInit, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, regularization, regularizationBias, updater, updater, weightDecay, weightDecay, weightDecayBias, weightDecayBias, weightInit, weightInit, weightInit, weightNoise
build, constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name
protected RNNFormat rnnDataFormat
protected List<LayerConstraint> recurrentConstraints
protected List<LayerConstraint> inputWeightConstraints
protected IWeightInit weightInitFnRecurrent
public T constrainRecurrent(LayerConstraint... constraints)
constraints
 Constraints to apply to the recurrent weight parameters of this layerpublic T constrainInputWeights(LayerConstraint... constraints)
constraints
 Constraints to apply to the input weight parameters of this layerpublic T weightInitRecurrent(IWeightInit weightInit)
weightInit
 Weight initialization for the recurrent weights only.public T weightInitRecurrent(WeightInit weightInit)
weightInit
 Weight initialization for the recurrent weights only.public T weightInitRecurrent(Distribution dist)
dist
 Distribution to use for initializing the recurrent weightsCopyright © 2020. All rights reserved.