org.deeplearning4j.nn.layers.feedforward.autoencoder

Class AutoEncoder

java.lang.Object

org.deeplearning4j.nn.layers.AbstractLayer<LayerConfT>

org.deeplearning4j.nn.layers.BaseLayer<LayerConfT>

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

org.deeplearning4j.nn.layers.feedforward.autoencoder.AutoEncoder

All Implemented Interfaces:

Serializable, Cloneable, Layer, Model

public class AutoEncoder
extends BasePretrainNetwork<AutoEncoder>

Autoencoder. Add Gaussian noise to input and learn a reconstruction function.

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from interface org.deeplearning4j.nn.api.Layer

Layer.TrainingMode, Layer.Type

Field Summary

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

gradient, gradientsFlattened, gradientViews, optimizer, params, paramsFlattened, score, solver, weightNoiseParams

Fields inherited from class org.deeplearning4j.nn.layers.AbstractLayer

cacheMode, conf, dropoutApplied, dropoutMask, epochCount, index, input, iterationCount, maskArray, maskState, preOutput, trainingListeners

Constructor Summary

Constructors

Constructor and Description
AutoEncoder(NeuralNetConfiguration conf)
AutoEncoder(NeuralNetConfiguration conf, org.nd4j.linalg.api.ndarray.INDArray input)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	activate(boolean training, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the last set input
org.nd4j.linalg.api.ndarray.INDArray	activate(org.nd4j.linalg.api.ndarray.INDArray input, boolean training, LayerWorkspaceMgr workspaceMgr) Perform forward pass and return the activations array with the specified input
void	computeGradientAndScore(LayerWorkspaceMgr workspaceMgr) Update the score
org.nd4j.linalg.api.ndarray.INDArray	decode(org.nd4j.linalg.api.ndarray.INDArray y, LayerWorkspaceMgr workspaceMgr)
org.nd4j.linalg.api.ndarray.INDArray	encode(org.nd4j.linalg.api.ndarray.INDArray v, boolean training, LayerWorkspaceMgr workspaceMgr)
boolean	isPretrainLayer() Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)
org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	sampleHiddenGivenVisible(org.nd4j.linalg.api.ndarray.INDArray v) Sample the hidden distribution given the visible
org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray>	sampleVisibleGivenHidden(org.nd4j.linalg.api.ndarray.INDArray h) Sample the visible distribution given the hidden

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

backpropGradient, calcL1, calcL2, createGradient, getCorruptedInput, numParams, numParams, params, paramTable, setParams, setScoreWithZ

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

accumulateScore, clear, clearNoiseWeightParams, clone, fit, fit, getGradientsViewArray, getOptimizer, getParam, getParamWithNoise, gradient, hasBias, initParams, layerConf, paramTable, preOutput, score, setBackpropGradientsViewArray, setParam, setParams, setParamsViewArray, setParamTable, toString, transpose, update, update

Methods inherited from class org.deeplearning4j.nn.layers.AbstractLayer

addListeners, applyConstraints, applyDropOutIfNecessary, applyMask, assertInputSet, batchSize, conf, feedForwardMaskArray, getIndex, getInput, getInputMiniBatchSize, getListeners, getMaskArray, gradientAndScore, init, input, layerId, setCacheMode, setConf, setIndex, setInput, setInputMiniBatchSize, setListeners, setListeners, setMaskArray, type, validateInput

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.nn.api.Layer

getEpochCount, getIterationCount, setEpochCount, setIterationCount

Constructor Detail

AutoEncoder

public AutoEncoder(NeuralNetConfiguration conf)

AutoEncoder

public AutoEncoder(NeuralNetConfiguration conf,
                   org.nd4j.linalg.api.ndarray.INDArray input)

Method Detail

sampleHiddenGivenVisible

public org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray> sampleHiddenGivenVisible(org.nd4j.linalg.api.ndarray.INDArray v)

Description copied from class: BasePretrainNetwork

Sample the hidden distribution given the visible

Specified by:

sampleHiddenGivenVisible in class BasePretrainNetwork<AutoEncoder>

Parameters:

v - the visible to sample from

Returns:

the hidden mean and sample

sampleVisibleGivenHidden

public org.nd4j.linalg.primitives.Pair<org.nd4j.linalg.api.ndarray.INDArray,org.nd4j.linalg.api.ndarray.INDArray> sampleVisibleGivenHidden(org.nd4j.linalg.api.ndarray.INDArray h)

Description copied from class: BasePretrainNetwork

Sample the visible distribution given the hidden

Specified by:

sampleVisibleGivenHidden in class BasePretrainNetwork<AutoEncoder>

Parameters:

h - the hidden to sample from

Returns:

the mean and sample

encode

public org.nd4j.linalg.api.ndarray.INDArray encode(org.nd4j.linalg.api.ndarray.INDArray v,
                                                   boolean training,
                                                   LayerWorkspaceMgr workspaceMgr)

decode

public org.nd4j.linalg.api.ndarray.INDArray decode(org.nd4j.linalg.api.ndarray.INDArray y,
                                                   LayerWorkspaceMgr workspaceMgr)

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input,
                                                     boolean training,
                                                     LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Perform forward pass and return the activations array with the specified input

Specified by:

activate in interface Layer

Overrides:

activate in class AbstractLayer<AutoEncoder>

Parameters:

input - the input to use

training - train or test mode

workspaceMgr - Workspace manager.

Returns:

Activations array. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

isPretrainLayer

public boolean isPretrainLayer()

Description copied from interface: Layer

Returns true if the layer can be trained in an unsupervised/pretrain manner (AE, VAE, etc)

Returns:

true if the layer can be pretrained (using fit(INDArray), false otherwise

activate

public org.nd4j.linalg.api.ndarray.INDArray activate(boolean training,
                                                     LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Layer

Perform forward pass and return the activations array with the last set input

Specified by:

activate in interface Layer

Overrides:

activate in class BaseLayer<AutoEncoder>

Parameters:

training - training or test mode

workspaceMgr - Workspace manager

Returns:

the activation (layer output) of the last specified input. Note that the returned array should be placed in the ArrayType.ACTIVATIONS workspace via the workspace manager

computeGradientAndScore

public void computeGradientAndScore(LayerWorkspaceMgr workspaceMgr)

Description copied from interface: Model

Update the score

Specified by:

computeGradientAndScore in interface Model

Overrides:

computeGradientAndScore in class BaseLayer<AutoEncoder>