Package org.deeplearning4j.nn.conf.layers

Class AutoEncoder.Builder

java.lang.Object

org.deeplearning4j.nn.conf.layers.Layer.Builder<T>

org.deeplearning4j.nn.conf.layers.BaseLayer.Builder<T>

org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder<T>

org.deeplearning4j.nn.conf.layers.BasePretrainNetwork.Builder<AutoEncoder.Builder>

org.deeplearning4j.nn.conf.layers.AutoEncoder.Builder

Enclosing class:

AutoEncoder

public static class AutoEncoder.Builder
extends BasePretrainNetwork.Builder<AutoEncoder.Builder>

Field Summary

Fields inherited from class org.deeplearning4j.nn.conf.layers.BasePretrainNetwork.Builder

lossFunction, visibleBiasInit

Fields inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder

nIn, nOut

Fields inherited from class org.deeplearning4j.nn.conf.layers.BaseLayer.Builder

activationFn, biasInit, biasUpdater, gainInit, gradientNormalization, gradientNormalizationThreshold, iupdater, regularization, regularizationBias, weightInitFn, weightNoise

Fields inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

allParamConstraints, biasConstraints, iDropout, layerName, weightConstraints

Constructor Summary

Constructors

Constructor	Description
Builder()
Builder(double corruptionLevel)	Builder - sets the level of corruption - 0.0 (none) to 1.0 (all values corrupted)

Method Summary

Modifier and Type	Method	Description
AutoEncoder	build()
AutoEncoder.Builder	corruptionLevel(double corruptionLevel)	Level of corruption - 0.0 (none) to 1.0 (all values corrupted)
AutoEncoder.Builder	sparsity(double sparsity)	Autoencoder sparity parameter

Methods inherited from class org.deeplearning4j.nn.conf.layers.BasePretrainNetwork.Builder

lossFunction, visibleBiasInit

Methods inherited from class org.deeplearning4j.nn.conf.layers.FeedForwardLayer.Builder

nIn, nIn, nOut, nOut, units

Methods inherited from class org.deeplearning4j.nn.conf.layers.BaseLayer.Builder

activation, activation, biasInit, biasUpdater, dist, gainInit, gradientNormalization, gradientNormalizationThreshold, l1, l1Bias, l2, l2Bias, regularization, regularizationBias, updater, updater, weightDecay, weightDecay, weightDecayBias, weightDecayBias, weightInit, weightInit, weightInit, weightNoise

Methods inherited from class org.deeplearning4j.nn.conf.layers.Layer.Builder

constrainAllParameters, constrainBias, constrainWeights, dropOut, dropOut, name

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

Builder

public Builder()

Builder

public Builder(double corruptionLevel)

Builder - sets the level of corruption - 0.0 (none) to 1.0 (all values corrupted)

Parameters:

corruptionLevel - Corruption level (0 to 1)

Method Detail

corruptionLevel

public AutoEncoder.Builder corruptionLevel(double corruptionLevel)

Level of corruption - 0.0 (none) to 1.0 (all values corrupted)

Parameters:

corruptionLevel - Corruption level (0 to 1)

sparsity

public AutoEncoder.Builder sparsity(double sparsity)

Autoencoder sparity parameter

Parameters:

sparsity - Sparsity

build

public AutoEncoder build()

Specified by:

build in class Layer.Builder<AutoEncoder.Builder>