VariationalAutoencoder

java.lang.Object
- org.deeplearning4j.nn.layers.variational.VariationalAutoencoder

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Layer, Model
```
public class VariationalAutoencoder
extends java.lang.Object
implements Layer
```
Variational Autoencoder layer
See: Kingma & Welling, 2013: Auto-Encoding Variational Bayes - https://arxiv.org/abs/1312.6114
This implementation allows multiple encoder and decoder layers, the number and sizes of which can be set independently.
A note on scores during pretraining: This implementation minimizes the negative of the variational lower bound objective as described in Kingma & Welling; the mathematics in that paper is based on maximization of the variational lower bound instead. Thus, scores reported during pretraining in DL4J are the negative of the variational lower bound equation in the paper. The backpropagation and learning procedure is otherwise as described there.

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
Modifier and Type	Field and Description
`protected NeuralNetConfiguration`	`conf`
`protected int[]`	`decoderLayerSizes`
`protected int[]`	`encoderLayerSizes`
`protected Gradient`	`gradient`
`protected org.nd4j.linalg.api.ndarray.INDArray`	`gradientsFlattened`
`protected java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>`	`gradientViews`
`protected int`	`index`
`protected org.nd4j.linalg.api.ndarray.INDArray`	`input`
`protected java.util.Collection<IterationListener>`	`iterationListeners`
`protected org.nd4j.linalg.api.ndarray.INDArray`	`maskArray`
`protected int`	`numSamples`
`protected ConvexOptimizer`	`optimizer`
`protected java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>`	`params`
`protected org.nd4j.linalg.api.ndarray.INDArray`	`paramsFlattened`
`protected org.nd4j.linalg.activations.IActivation`	`pzxActivationFn`
`protected ReconstructionDistribution`	`reconstructionDistribution`
`protected double`	`score`
`protected Solver`	`solver`
`protected java.util.Collection<TrainingListener>`	`trainingListeners`
`protected boolean`	`zeroedPretrainParamGradients`

Constructor Summary

Constructors
Constructor and Description

VariationalAutoencoder(NeuralNetConfiguration conf)

Constructors
Constructor and Description
`VariationalAutoencoder(NeuralNetConfiguration conf)`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`void`	`accumulateScore(double accum)` Sets a rolling tally for the score.
`org.nd4j.linalg.api.ndarray.INDArray`	`activate()` Trigger an activation with the last specified input
`org.nd4j.linalg.api.ndarray.INDArray`	`activate(boolean training)` Trigger an activation with the last specified input
`org.nd4j.linalg.api.ndarray.INDArray`	`activate(org.nd4j.linalg.api.ndarray.INDArray input)` Initialize the layer with the given input and return the activation for this layer given this input
`org.nd4j.linalg.api.ndarray.INDArray`	`activate(org.nd4j.linalg.api.ndarray.INDArray input, boolean training)` Initialize the layer with the given input and return the activation for this layer given this input
`org.nd4j.linalg.api.ndarray.INDArray`	`activate(org.nd4j.linalg.api.ndarray.INDArray input, Layer.TrainingMode training)` Initialize the layer with the given input and return the activation for this layer given this input
`org.nd4j.linalg.api.ndarray.INDArray`	`activate(Layer.TrainingMode training)` Trigger an activation with the last specified input
`org.nd4j.linalg.api.ndarray.INDArray`	`activationMean()` Calculate the mean representation for the activation for this layer
`void`	`applyLearningRateScoreDecay()` Update learningRate using for this model.
`Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray>`	`backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)` Calculate the gradient relative to the error in the next layer
`int`	`batchSize()` The current inputs batch size
`Gradient`	`calcGradient(Gradient layerError, org.nd4j.linalg.api.ndarray.INDArray indArray)` Calculate the gradient
`double`	`calcL1(boolean backpropParamsOnly)` Calculate the l1 regularization term 0.0 if regularization is not used.
`double`	`calcL2(boolean backpropParamsOnly)` Calculate the l2 regularization term 0.0 if regularization is not used.
`void`	`clear()` Clear input
`Layer`	`clone()` Clone the layer
`void`	`computeGradientAndScore()` Update the score
`NeuralNetConfiguration`	`conf()` The configuration for the neural network
`org.nd4j.linalg.api.ndarray.INDArray`	`derivativeActivation(org.nd4j.linalg.api.ndarray.INDArray input)` Take the derivative of the given input based on the activation
`Gradient`	`error(org.nd4j.linalg.api.ndarray.INDArray input)` Calculate error with respect to the current layer.
`Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState>`	`feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray, MaskState currentMaskState, int minibatchSize)` Feed forward the input mask array, setting in in the layer as appropriate.
`void`	`fit()` All models have a fit method
`void`	`fit(org.nd4j.linalg.api.ndarray.INDArray data)` Fit the model to the given data
`org.nd4j.linalg.api.ndarray.INDArray`	`generateAtMeanGivenZ(org.nd4j.linalg.api.ndarray.INDArray latentSpaceValues)` Given a specified values for the latent space as input (latent space being z in p(z\|data)), generate output from P(x\|z), where x = E[P(x\|z)] i.e., return the mean value for the distribution P(x\|z)
`org.nd4j.linalg.api.ndarray.INDArray`	`generateRandomGivenZ(org.nd4j.linalg.api.ndarray.INDArray latentSpaceValues)` Given a specified values for the latent space as input (latent space being z in p(z\|data)), randomly generate output x, where x ~ P(x\|z)
`int`	`getIndex()` Get the layer index.
`int`	`getInputMiniBatchSize()` Get current/last input mini-batch size, as set by setInputMiniBatchSize(int)
`java.util.Collection<IterationListener>`	`getListeners()` Get the iteration listeners for this layer.
`org.nd4j.linalg.api.ndarray.INDArray`	`getMaskArray()`
`ConvexOptimizer`	`getOptimizer()` Returns this models optimizer
`org.nd4j.linalg.api.ndarray.INDArray`	`getParam(java.lang.String param)` Get the parameter
`Gradient`	`gradient()` Calculate a gradient
`Pair<Gradient,java.lang.Double>`	`gradientAndScore()` Get the gradient and score
`boolean`	`hasLossFunction()` Does the reconstruction distribution have a loss function (such as mean squared error) or is it a standard probabilistic reconstruction distribution?
`void`	`init()` Init the model
`void`	`initParams()` Initialize the parameters
`org.nd4j.linalg.api.ndarray.INDArray`	`input()` The input/feature matrix for the model
`boolean`	`isPretrainLayer()` Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)
`boolean`	`isPretrainParam(java.lang.String param)`
`void`	`iterate(org.nd4j.linalg.api.ndarray.INDArray input)` Run one iteration
`void`	`merge(Layer layer, int batchSize)` Parameter averaging
`int`	`numParams()` the number of parameters for the model
`int`	`numParams(boolean backwards)` the number of parameters for the model
`org.nd4j.linalg.api.ndarray.INDArray`	`params()` Parameters of the model (if any)
`java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>`	`paramTable()` The param table
`java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray>`	`paramTable(boolean backpropParamsOnly)` Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
`org.nd4j.linalg.api.ndarray.INDArray`	`preOutput(boolean training)`
`org.nd4j.linalg.api.ndarray.INDArray`	`preOutput(org.nd4j.linalg.api.ndarray.INDArray x)` Raw activations
`org.nd4j.linalg.api.ndarray.INDArray`	`preOutput(org.nd4j.linalg.api.ndarray.INDArray x, boolean training)` Raw activations
`org.nd4j.linalg.api.ndarray.INDArray`	`preOutput(org.nd4j.linalg.api.ndarray.INDArray x, Layer.TrainingMode training)` Raw activations
`org.nd4j.linalg.api.ndarray.INDArray`	`reconstructionError(org.nd4j.linalg.api.ndarray.INDArray data)` Return the reconstruction error for this variational autoencoder. NOTE (important): This method is used ONLY for VAEs that have a standard neural network loss function (i.e., an `ILossFunction` instance such as mean squared error) instead of using a probabilistic reconstruction distribution P(x\|z) for the reconstructions (as presented in the VAE architecture by Kingma and Welling). You can check if the VAE has a loss function using `hasLossFunction()` Consequently, the reconstruction error is a simple deterministic function (no Monte-Carlo sampling is required, unlike `reconstructionProbability(INDArray, int)` and `reconstructionLogProbability(INDArray, int)`)
`org.nd4j.linalg.api.ndarray.INDArray`	`reconstructionLogProbability(org.nd4j.linalg.api.ndarray.INDArray data, int numSamples)` Return the log reconstruction probability given the specified number of samples. See `reconstructionLogProbability(INDArray, int)` for more details
`org.nd4j.linalg.api.ndarray.INDArray`	`reconstructionProbability(org.nd4j.linalg.api.ndarray.INDArray data, int numSamples)` Calculate the reconstruction probability, as described in An & Cho, 2015 - "Variational Autoencoder based Anomaly Detection using Reconstruction Probability" (Algorithm 4) The authors describe it as follows: "This is essentially the probability of the data being generated from a given latent variable drawn from the approximate posterior distribution." Specifically, for each example x in the input, calculate p(x).
`double`	`score()` The score for the model
`void`	`setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray gradients)` Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
`void`	`setConf(NeuralNetConfiguration conf)` Setter for the configuration
`void`	`setIndex(int index)` Set the layer index.
`void`	`setInput(org.nd4j.linalg.api.ndarray.INDArray input)` Get the layer input.
`void`	`setInputMiniBatchSize(int size)` Set current/last input mini-batch size. Used for score and gradient calculations.
`void`	`setListeners(java.util.Collection<IterationListener> listeners)` Set the iteration listeners for this layer.
`void`	`setListeners(IterationListener... listeners)` Set the iteration listeners for this layer.
`void`	`setMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray)` Set the mask array.
`void`	`setParam(java.lang.String key, org.nd4j.linalg.api.ndarray.INDArray val)` Set the parameter with a new ndarray
`void`	`setParams(org.nd4j.linalg.api.ndarray.INDArray params)` Set the parameters for this model.
`void`	`setParamsViewArray(org.nd4j.linalg.api.ndarray.INDArray params)` Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
`void`	`setParamTable(java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)` Setter for the param table
`Layer`	`transpose()` Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)
`Layer.Type`	`type()` Returns the layer type
`void`	`update(Gradient gradient)` Update layer weights and biases with gradient change
`void`	`update(org.nd4j.linalg.api.ndarray.INDArray gradient, java.lang.String paramType)` Perform one update applying the gradient
`void`	`validateInput()` Validate the input

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - input
```
protected org.nd4j.linalg.api.ndarray.INDArray input
```
  - paramsFlattened
```
protected org.nd4j.linalg.api.ndarray.INDArray paramsFlattened
```
  - gradientsFlattened
```
protected org.nd4j.linalg.api.ndarray.INDArray gradientsFlattened
```
  - params
```
protected java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> params
```
  - gradientViews
```
protected transient java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> gradientViews
```
  - conf
```
protected NeuralNetConfiguration conf
```
  - score
```
protected double score
```
  - optimizer
```
protected ConvexOptimizer optimizer
```
  - gradient
```
protected Gradient gradient
```
  - iterationListeners
```
protected java.util.Collection<IterationListener> iterationListeners
```
  - trainingListeners
```
protected java.util.Collection<TrainingListener> trainingListeners
```
  - index
```
protected int index
```
  - maskArray
```
protected org.nd4j.linalg.api.ndarray.INDArray maskArray
```
  - solver
```
protected Solver solver
```
  - encoderLayerSizes
```
protected int[] encoderLayerSizes
```
  - decoderLayerSizes
```
protected int[] decoderLayerSizes
```
  - reconstructionDistribution
```
protected ReconstructionDistribution reconstructionDistribution
```
  - pzxActivationFn
```
protected org.nd4j.linalg.activations.IActivation pzxActivationFn
```
  - numSamples
```
protected int numSamples
```
  - zeroedPretrainParamGradients
```
protected boolean zeroedPretrainParamGradients
```
- Constructor Detail
  - VariationalAutoencoder
```
public VariationalAutoencoder(NeuralNetConfiguration conf)
```
- Method Detail
  - init
```
public void init()
```
    Init the model
    
    Specified by:
    
    init in interface Model
  - update
```
public void update(Gradient gradient)
```
    Description copied from interface: Model
    
    Update layer weights and biases with gradient change
    
    Specified by:
    
    update in interface Model
  - update
```
public void update(org.nd4j.linalg.api.ndarray.INDArray gradient,
                   java.lang.String paramType)
```
    Description copied from interface: Model
    
    Perform one update applying the gradient
    
    Specified by:
    
    update in interface Model
    
    Parameters:
    
    gradient - the gradient to apply
  - score
```
public double score()
```
    Description copied from interface: Model
    
    The score for the model
    
    Specified by:
    
    score in interface Model
    
    Returns:
    
    the score for the model
  - computeGradientAndScore
```
public void computeGradientAndScore()
```
    Description copied from interface: Model
    
    Update the score
    
    Specified by:
    
    computeGradientAndScore in interface Model
  - accumulateScore
```
public void accumulateScore(double accum)
```
    Description copied from interface: Model
    
    Sets a rolling tally for the score. This is useful for mini batch learning when you are accumulating error across a dataset.
    
    Specified by:
    
    accumulateScore in interface Model
    
    Parameters:
    
    accum - the amount to accum
  - params
```
public org.nd4j.linalg.api.ndarray.INDArray params()
```
    Description copied from interface: Model
    
    Parameters of the model (if any)
    
    Specified by:
    
    params in interface Model
    
    Returns:
    
    the parameters of the model
  - numParams
```
public int numParams()
```
    Description copied from interface: Model
    
    the number of parameters for the model
    
    Specified by:
    
    numParams in interface Model
    
    Returns:
    
    the number of parameters for the model
  - numParams
```
public int numParams(boolean backwards)
```
    Description copied from interface: Model
    
    the number of parameters for the model
    
    Specified by:
    
    numParams in interface Model
    
    Returns:
    
    the number of parameters for the model
  - setParams
```
public void setParams(org.nd4j.linalg.api.ndarray.INDArray params)
```
    Description copied from interface: Model
    
    Set the parameters for this model. This expects a linear ndarray which then be unpacked internally relative to the expected ordering of the model
    
    Specified by:
    
    setParams in interface Model
    
    Parameters:
    
    params - the parameters for the model
  - setParamsViewArray
```
public void setParamsViewArray(org.nd4j.linalg.api.ndarray.INDArray params)
```
    Description copied from interface: Model
    
    Set the initial parameters array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
    
    Specified by:
    
    setParamsViewArray in interface Model
    
    Parameters:
    
    params - a 1 x nParams row vector that is a view of the larger (MLN/CG) parameters array
  - setBackpropGradientsViewArray
```
public void setBackpropGradientsViewArray(org.nd4j.linalg.api.ndarray.INDArray gradients)
```
    Description copied from interface: Model
    
    Set the gradients array as a view of the full (backprop) network parameters NOTE: this is intended to be used internally in MultiLayerNetwork and ComputationGraph, not by users.
    
    Specified by:
    
    setBackpropGradientsViewArray in interface Model
    
    Parameters:
    
    gradients - a 1 x nParams row vector that is a view of the larger (MLN/CG) gradients array
  - applyLearningRateScoreDecay
```
public void applyLearningRateScoreDecay()
```
    Description copied from interface: Model
    
    Update learningRate using for this model. Use the learningRateScoreBasedDecay to adapt the score if the Eps termination condition is met
    
    Specified by:
    
    applyLearningRateScoreDecay in interface Model
  - fit
```
public void fit(org.nd4j.linalg.api.ndarray.INDArray data)
```
    Description copied from interface: Model
    
    Fit the model to the given data
    
    Specified by:
    
    fit in interface Model
    
    Parameters:
    
    data - the data to fit the model to
  - iterate
```
public void iterate(org.nd4j.linalg.api.ndarray.INDArray input)
```
    Description copied from interface: Model
    
    Run one iteration
    
    Specified by:
    
    iterate in interface Model
    
    Parameters:
    
    input - the input to iterate on
  - gradient
```
public Gradient gradient()
```
    Description copied from interface: Model
    
    Calculate a gradient
    
    Specified by:
    
    gradient in interface Model
    
    Returns:
    
    the gradient for this model
  - gradientAndScore
```
public Pair<Gradient,java.lang.Double> gradientAndScore()
```
    Description copied from interface: Model
    
    Get the gradient and score
    
    Specified by:
    
    gradientAndScore in interface Model
    
    Returns:
    
    the gradient and score
  - batchSize
```
public int batchSize()
```
    Description copied from interface: Model
    
    The current inputs batch size
    
    Specified by:
    
    batchSize in interface Model
    
    Returns:
    
    the current inputs batch size
  - conf
```
public NeuralNetConfiguration conf()
```
    Description copied from interface: Model
    
    The configuration for the neural network
    
    Specified by:
    
    conf in interface Model
    
    Returns:
    
    the configuration for the neural network
  - setConf
```
public void setConf(NeuralNetConfiguration conf)
```
    Description copied from interface: Model
    
    Setter for the configuration
    
    Specified by:
    
    setConf in interface Model
  - input
```
public org.nd4j.linalg.api.ndarray.INDArray input()
```
    Description copied from interface: Model
    
    The input/feature matrix for the model
    
    Specified by:
    
    input in interface Model
    
    Returns:
    
    the input/feature matrix for the model
  - validateInput
```
public void validateInput()
```
    Description copied from interface: Model
    
    Validate the input
    
    Specified by:
    
    validateInput in interface Model
  - getOptimizer
```
public ConvexOptimizer getOptimizer()
```
    Description copied from interface: Model
    
    Returns this models optimizer
    
    Specified by:
    
    getOptimizer in interface Model
    
    Returns:
    
    this models optimizer
  - getParam
```
public org.nd4j.linalg.api.ndarray.INDArray getParam(java.lang.String param)
```
    Description copied from interface: Model
    
    Get the parameter
    
    Specified by:
    
    getParam in interface Model
    
    Parameters:
    
    param - the key of the parameter
    
    Returns:
    
    the parameter vector/matrix with that particular key
  - initParams
```
public void initParams()
```
    Description copied from interface: Model
    
    Initialize the parameters
    
    Specified by:
    
    initParams in interface Model
  - paramTable
```
public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable()
```
    Description copied from interface: Model
    
    The param table
    
    Specified by:
    
    paramTable in interface Model
    
    Returns:
  - paramTable
```
public java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable(boolean backpropParamsOnly)
```
    Description copied from interface: Model
    
    Table of parameters by key, for backprop For many models (dense layers, etc) - all parameters are backprop parameters
    
    Specified by:
    
    paramTable in interface Model
    
    Parameters:
    
    backpropParamsOnly - If true, return backprop params only. If false: return all params (equivalent to paramsTable())
  - setParamTable
```
public void setParamTable(java.util.Map<java.lang.String,org.nd4j.linalg.api.ndarray.INDArray> paramTable)
```
    Description copied from interface: Model
    
    Setter for the param table
    
    Specified by:
    
    setParamTable in interface Model
  - setParam
```
public void setParam(java.lang.String key,
                     org.nd4j.linalg.api.ndarray.INDArray val)
```
    Description copied from interface: Model
    
    Set the parameter with a new ndarray
    
    Specified by:
    
    setParam in interface Model
    
    Parameters:
    
    key - the key to se t
    
    val - the new ndarray
  - clear
```
public void clear()
```
    Description copied from interface: Model
    
    Clear input
    
    Specified by:
    
    clear in interface Model
  - isPretrainParam
```
public boolean isPretrainParam(java.lang.String param)
```
  - calcL2
```
public double calcL2(boolean backpropParamsOnly)
```
    Description copied from interface: Layer
    
    Calculate the l2 regularization term
    0.0 if regularization is not used. Or 0.5 * l2Coeff * l2Magnitude otherwise.
    Note that this does not divide by mini-batch size
    
    Specified by:
    
    calcL2 in interface Layer
    
    Parameters:
    
    backpropParamsOnly - If true: calculate L2 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)
    
    Returns:
    
    the l2 regularization term for this layer.
  - calcL1
```
public double calcL1(boolean backpropParamsOnly)
```
    Description copied from interface: Layer
    
    Calculate the l1 regularization term
    0.0 if regularization is not used. Or l1Coeff * l1Magnitude otherwise.
    Note that this does not divide by mini-batch size
    
    Specified by:
    
    calcL1 in interface Layer
    
    Parameters:
    
    backpropParamsOnly - If true: calculate L1 based on backprop params only. If false: calculate based on all params (including pretrain params, if any)
    
    Returns:
    
    the l1 regularization term for this layer.
  - type
```
public Layer.Type type()
```
    Description copied from interface: Layer
    
    Returns the layer type
    
    Specified by:
    
    type in interface Layer
    
    Returns:
  - error
```
public Gradient error(org.nd4j.linalg.api.ndarray.INDArray input)
```
    Description copied from interface: Layer
    
    Calculate error with respect to the current layer. This gradient will contain the error signal
    
    Specified by:
    
    error in interface Layer
    
    Parameters:
    
    input - the gradient for the forward layer If this is the final layer, it will start with the error from the output. This is on the user to initialize.
    
    Returns:
    
    the gradient wrt the parameters on the current layer
  - derivativeActivation
```
public org.nd4j.linalg.api.ndarray.INDArray derivativeActivation(org.nd4j.linalg.api.ndarray.INDArray input)
```
    Description copied from interface: Layer
    
    Take the derivative of the given input based on the activation
    
    Specified by:
    
    derivativeActivation in interface Layer
    
    Parameters:
    
    input - the input to take the derivative of
    
    Returns:
    
    the derivative of the action
  - calcGradient
```
public Gradient calcGradient(Gradient layerError,
                             org.nd4j.linalg.api.ndarray.INDArray indArray)
```
    Description copied from interface: Layer
    
    Calculate the gradient
    
    Specified by:
    
    calcGradient in interface Layer
    
    Parameters:
    
    layerError - the layer error
    
    Returns:
    
    the gradient
  - backpropGradient
```
public Pair<Gradient,org.nd4j.linalg.api.ndarray.INDArray> backpropGradient(org.nd4j.linalg.api.ndarray.INDArray epsilon)
```
    Description copied from interface: Layer
    
    Calculate the gradient relative to the error in the next layer
    
    Specified by:
    
    backpropGradient in interface Layer
    
    Parameters:
    
    epsilon - w^(L+1)*delta^(L+1). Or, equiv: dC/da, i.e., (dC/dz)*(dz/da) = dC/da, where C is cost function a=sigma(z) is activation.
    
    Returns:
    
    Pair where Gradient is gradient for this layer, INDArray is epsilon needed by next layer, but before element-wise multiply by sigmaPrime(z). So for standard feed-forward layer, if this layer is L, then return.getSecond() == (w^(L)*(delta^(L))^T)^T
  - merge
```
public void merge(Layer layer,
                  int batchSize)
```
    Description copied from interface: Layer
    
    Parameter averaging
    
    Specified by:
    
    merge in interface Layer
    
    Parameters:
    
    layer - the layer to merge
    
    batchSize - the batch size to merge on
  - activationMean
```
public org.nd4j.linalg.api.ndarray.INDArray activationMean()
```
    Description copied from interface: Layer
    
    Calculate the mean representation for the activation for this layer
    
    Specified by:
    
    activationMean in interface Layer
    
    Returns:
    
    the activation mean for this layer
  - preOutput
```
public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x)
```
    Description copied from interface: Layer
    
    Raw activations
    
    Specified by:
    
    preOutput in interface Layer
    
    Parameters:
    
    x - the input to transform
    
    Returns:
    
    the raw activation for this layer
  - preOutput
```
public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x,
                                                      Layer.TrainingMode training)
```
    Description copied from interface: Layer
    
    Raw activations
    
    Specified by:
    
    preOutput in interface Layer
    
    Parameters:
    
    x - the input to transform
    
    Returns:
    
    the raw activation for this layer
  - preOutput
```
public org.nd4j.linalg.api.ndarray.INDArray preOutput(org.nd4j.linalg.api.ndarray.INDArray x,
                                                      boolean training)
```
    Description copied from interface: Layer
    
    Raw activations
    
    Specified by:
    
    preOutput in interface Layer
    
    Parameters:
    
    x - the input to transform
    
    Returns:
    
    the raw activation for this layer
  - preOutput
```
public org.nd4j.linalg.api.ndarray.INDArray preOutput(boolean training)
```
  - activate
```
public org.nd4j.linalg.api.ndarray.INDArray activate(Layer.TrainingMode training)
```
    Description copied from interface: Layer
    
    Trigger an activation with the last specified input
    
    Specified by:
    
    activate in interface Layer
    
    Parameters:
    
    training - training or test mode
    
    Returns:
    
    the activation of the last specified input
  - activate
```
public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input,
                                                     Layer.TrainingMode training)
```
    Description copied from interface: Layer
    
    Initialize the layer with the given input and return the activation for this layer given this input
    
    Specified by:
    
    activate in interface Layer
    
    Parameters:
    
    input - the input to use
    
    training - train or test mode
    
    Returns:
  - activate
```
public org.nd4j.linalg.api.ndarray.INDArray activate(boolean training)
```
    Description copied from interface: Layer
    
    Trigger an activation with the last specified input
    
    Specified by:
    
    activate in interface Layer
    
    Parameters:
    
    training - training or test mode
    
    Returns:
    
    the activation of the last specified input
  - activate
```
public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input,
                                                     boolean training)
```
    Description copied from interface: Layer
    
    Initialize the layer with the given input and return the activation for this layer given this input
    
    Specified by:
    
    activate in interface Layer
    
    Parameters:
    
    input - the input to use
    
    training - train or test mode
    
    Returns:
  - activate
```
public org.nd4j.linalg.api.ndarray.INDArray activate()
```
    Description copied from interface: Layer
    
    Trigger an activation with the last specified input
    
    Specified by:
    
    activate in interface Layer
    
    Returns:
    
    the activation of the last specified input
  - activate
```
public org.nd4j.linalg.api.ndarray.INDArray activate(org.nd4j.linalg.api.ndarray.INDArray input)
```
    Description copied from interface: Layer
    
    Initialize the layer with the given input and return the activation for this layer given this input
    
    Specified by:
    
    activate in interface Layer
    
    Parameters:
    
    input - the input to use
    
    Returns:
  - transpose
```
public Layer transpose()
```
    Description copied from interface: Layer
    
    Return a transposed copy of the weights/bias (this means reverse the number of inputs and outputs on the weights)
    
    Specified by:
    
    transpose in interface Layer
    
    Returns:
    
    the transposed layer
  - clone
```
public Layer clone()
```
    Description copied from interface: Layer
    
    Clone the layer
    
    Specified by:
    
    clone in interface Layer
    
    Overrides:
    
    clone in class java.lang.Object
    
    Returns:
  - getListeners
```
public java.util.Collection<IterationListener> getListeners()
```
    Description copied from interface: Layer
    
    Get the iteration listeners for this layer.
    
    Specified by:
    
    getListeners in interface Layer
  - setListeners
```
public void setListeners(IterationListener... listeners)
```
    Description copied from interface: Layer
    
    Set the iteration listeners for this layer.
    
    Specified by:
    
    setListeners in interface Layer
    
    Specified by:
    
    setListeners in interface Model
  - setListeners
```
public void setListeners(java.util.Collection<IterationListener> listeners)
```
    Description copied from interface: Layer
    
    Set the iteration listeners for this layer.
    
    Specified by:
    
    setListeners in interface Layer
    
    Specified by:
    
    setListeners in interface Model
  - setIndex
```
public void setIndex(int index)
```
    Description copied from interface: Layer
    
    Set the layer index.
    
    Specified by:
    
    setIndex in interface Layer
  - getIndex
```
public int getIndex()
```
    Description copied from interface: Layer
    
    Get the layer index.
    
    Specified by:
    
    getIndex in interface Layer
  - setInput
```
public void setInput(org.nd4j.linalg.api.ndarray.INDArray input)
```
    Description copied from interface: Layer
    
    Get the layer input.
    
    Specified by:
    
    setInput in interface Layer
  - setInputMiniBatchSize
```
public void setInputMiniBatchSize(int size)
```
    Description copied from interface: Layer
    
    Set current/last input mini-batch size.
    Used for score and gradient calculations. Mini batch size may be different from getInput().size(0) due to reshaping operations - for example, when using RNNs with DenseLayer and OutputLayer. Called automatically during forward pass.
    
    Specified by:
    
    setInputMiniBatchSize in interface Layer
  - getInputMiniBatchSize
```
public int getInputMiniBatchSize()
```
    Description copied from interface: Layer
    
    Get current/last input mini-batch size, as set by setInputMiniBatchSize(int)
    
    Specified by:
    
    getInputMiniBatchSize in interface Layer
    
    See Also:
    
    Layer.setInputMiniBatchSize(int)
  - setMaskArray
```
public void setMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray)
```
    Description copied from interface: Layer
    
    Set the mask array. Note: In general, Layer.feedForwardMaskArray(INDArray, MaskState, int) should be used in preference to this.
    
    Specified by:
    
    setMaskArray in interface Layer
    
    Parameters:
    
    maskArray - Mask array to set
  - getMaskArray
```
public org.nd4j.linalg.api.ndarray.INDArray getMaskArray()
```
    Specified by:
    
    getMaskArray in interface Layer
  - isPretrainLayer
```
public boolean isPretrainLayer()
```
    Description copied from interface: Layer
    
    Returns true if the layer can be trained in an unsupervised/pretrain manner (VAE, RBMs etc)
    
    Specified by:
    
    isPretrainLayer in interface Layer
    
    Returns:
    
    true if the layer can be pretrained (using fit(INDArray), false otherwise
  - feedForwardMaskArray
```
public Pair<org.nd4j.linalg.api.ndarray.INDArray,MaskState> feedForwardMaskArray(org.nd4j.linalg.api.ndarray.INDArray maskArray,
                                                                                 MaskState currentMaskState,
                                                                                 int minibatchSize)
```
    Description copied from interface: Layer
    
    Feed forward the input mask array, setting in in the layer as appropriate. This allows different layers to handle masks differently - for example, bidirectional RNNs and normal RNNs operate differently with masks (the former sets activations to 0 outside of the data present region (and keeps the mask active for future layers like dense layers), whereas normal RNNs don't zero out the activations/errors )instead relying on backpropagated error arrays to handle the variable length case.
    This is also used for example for networks that contain global pooling layers, arbitrary preprocessors, etc.
    
    Specified by:
    
    feedForwardMaskArray in interface Layer
    
    Parameters:
    
    maskArray - Mask array to set
    
    currentMaskState - Current state of the mask - see MaskState
    
    minibatchSize - Current minibatch size. Needs to be known as it cannot always be inferred from the activations array due to reshaping (such as a DenseLayer within a recurrent neural network)
    
    Returns:
    
    New mask array after this layer, along with the new mask state.
  - fit
```
public void fit()
```
    Description copied from interface: Model
    
    All models have a fit method
    
    Specified by:
    
    fit in interface Model
  - reconstructionProbability
```
public org.nd4j.linalg.api.ndarray.INDArray reconstructionProbability(org.nd4j.linalg.api.ndarray.INDArray data,
                                                                      int numSamples)
```
    Calculate the reconstruction probability, as described in An & Cho, 2015 - "Variational Autoencoder based Anomaly Detection using Reconstruction Probability" (Algorithm 4)
    The authors describe it as follows: "This is essentially the probability of the data being generated from a given latent variable drawn from the approximate posterior distribution."
    
    Specifically, for each example x in the input, calculate p(x). Note however that p(x) is a stochastic (Monte-Carlo) estimate of the true p(x), based on the specified number of samples. More samples will produce a more accurate (lower variance) estimate of the true p(x) for the current model parameters.
    
    Internally uses reconstructionLogProbability(INDArray, int) for the actual implementation. That method may be more numerically stable in some cases.
    
    The returned array is a column vector of reconstruction probabilities, for each example. Thus, reconstruction probabilities can (and should, for efficiency) be calculated in a batched manner.
    
    Parameters:
    
    data - The data to calculate the reconstruction probability for
    
    numSamples - Number of samples with which to base the reconstruction probability on.
    
    Returns:
    
    Column vector of reconstruction probabilities for each example (shape: [numExamples,1])
  - reconstructionLogProbability
```
public org.nd4j.linalg.api.ndarray.INDArray reconstructionLogProbability(org.nd4j.linalg.api.ndarray.INDArray data,
                                                                         int numSamples)
```
    Return the log reconstruction probability given the specified number of samples.
    See reconstructionLogProbability(INDArray, int) for more details
    
    Parameters:
    
    data - The data to calculate the log reconstruction probability
    
    numSamples - Number of samples with which to base the reconstruction probability on.
    
    Returns:
    
    Column vector of reconstruction log probabilities for each example (shape: [numExamples,1])
  - generateAtMeanGivenZ
```
public org.nd4j.linalg.api.ndarray.INDArray generateAtMeanGivenZ(org.nd4j.linalg.api.ndarray.INDArray latentSpaceValues)
```
    Given a specified values for the latent space as input (latent space being z in p(z|data)), generate output from P(x|z), where x = E[P(x|z)]
    i.e., return the mean value for the distribution P(x|z)
    
    Parameters:
    
    latentSpaceValues - Values for the latent space. size(1) must equal nOut configuration parameter
    
    Returns:
    
    Sample of data: E[P(x|z)]
  - generateRandomGivenZ
```
public org.nd4j.linalg.api.ndarray.INDArray generateRandomGivenZ(org.nd4j.linalg.api.ndarray.INDArray latentSpaceValues)
```
    Given a specified values for the latent space as input (latent space being z in p(z|data)), randomly generate output x, where x ~ P(x|z)
    
    Parameters:
    
    latentSpaceValues - Values for the latent space. size(1) must equal nOut configuration parameter
    
    Returns:
    
    Sample of data: x ~ P(x|z)
  - hasLossFunction
```
public boolean hasLossFunction()
```
    Does the reconstruction distribution have a loss function (such as mean squared error) or is it a standard probabilistic reconstruction distribution?
  - reconstructionError
```
public org.nd4j.linalg.api.ndarray.INDArray reconstructionError(org.nd4j.linalg.api.ndarray.INDArray data)
```
    Return the reconstruction error for this variational autoencoder.
    NOTE (important): This method is used ONLY for VAEs that have a standard neural network loss function (i.e., an ILossFunction instance such as mean squared error) instead of using a probabilistic reconstruction distribution P(x|z) for the reconstructions (as presented in the VAE architecture by Kingma and Welling).
    You can check if the VAE has a loss function using hasLossFunction()
    Consequently, the reconstruction error is a simple deterministic function (no Monte-Carlo sampling is required, unlike reconstructionProbability(INDArray, int) and reconstructionLogProbability(INDArray, int))
    
    Parameters:
    
    data - The data to calculate the reconstruction error on
    
    Returns:
    
    Column vector of reconstruction errors for each example (shape: [numExamples,1])

Class VariationalAutoencoder

Nested Class Summary

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

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

input

paramsFlattened

gradientsFlattened

params

gradientViews

conf

score

optimizer

gradient

iterationListeners

trainingListeners

index

maskArray

solver

encoderLayerSizes

decoderLayerSizes

reconstructionDistribution

pzxActivationFn

numSamples

zeroedPretrainParamGradients

Constructor Detail

VariationalAutoencoder

Method Detail

init

update

update

score

computeGradientAndScore

accumulateScore

params

numParams

numParams

setParams

setParamsViewArray

setBackpropGradientsViewArray

applyLearningRateScoreDecay

fit

iterate

gradient

gradientAndScore

batchSize

conf

setConf

input

validateInput

getOptimizer

getParam

initParams

paramTable

paramTable

setParamTable

setParam

clear

isPretrainParam

calcL2

calcL1

type

error

derivativeActivation

calcGradient

backpropGradient

merge

activationMean

preOutput

preOutput

preOutput

preOutput

activate

activate

activate

activate

activate