GaussianReconstructionDistribution (deeplearning4j-nn 1.0.0-beta3 API)

java.lang.Object
- org.deeplearning4j.nn.conf.layers.variational.GaussianReconstructionDistribution

All Implemented Interfaces:

Serializable, ReconstructionDistribution
```
public class GaussianReconstructionDistribution
extends Object
implements ReconstructionDistribution
```
Gaussian reconstruction distribution for variational autoencoder.
Outputs are modelled by a Gaussian distribution, with the mean and variances (diagonal covariance matrix) for each output determined by the network forward pass.

Specifically, the GaussianReconstructionDistribution models mean and log(stdev^2). This parameterization gives log(1) = 0, and inputs can be in range (-infinity,infinity). Other parameterizations for variance are of course possible but may be problematic with respect to the average pre-activation function values and activation function ranges.
For activation functions, identity and perhaps tanh are typical - though tanh (unlike identity) implies a minimum/maximum possible value for mean and log variance. Asymmetric activation functions such as sigmoid or relu should be avoided.

Author:

Alex Black

See Also:

Serialized Form

Constructor Summary

Constructors
Constructor and Description
`GaussianReconstructionDistribution()` Create a GaussianReconstructionDistribution with the default identity activation function.
`GaussianReconstructionDistribution(Activation activationFn)`
`GaussianReconstructionDistribution(IActivation activationFn)`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`int`	`distributionInputSize(int dataSize)` Get the number of distribution parameters for the given input data size.
`INDArray`	`exampleNegLogProbability(INDArray x, INDArray preOutDistributionParams)` Calculate the negative log probability for each example individually
`INDArray`	`generateAtMean(INDArray preOutDistributionParams)` Generate a sample from P(x\|z), where x = E[P(x\|z)] i.e., return the mean value for the distribution
`INDArray`	`generateRandom(INDArray preOutDistributionParams)` Randomly sample from P(x\|z) using the specified distribution parameters
`INDArray`	`gradient(INDArray x, INDArray preOutDistributionParams)` Calculate the gradient of the negative log probability with respect to the preOutDistributionParams
`boolean`	`hasLossFunction()` Does this reconstruction distribution has a standard neural network loss function (such as mean squared error, which is deterministic) or is it a standard VAE with a probabilistic reconstruction distribution?
`double`	`negLogProbability(INDArray x, INDArray preOutDistributionParams, boolean average)` Calculate the negative log probability (summed or averaged over each example in the minibatch)
`String`	`toString()`

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

- Constructor Detail
  - GaussianReconstructionDistribution
```
public GaussianReconstructionDistribution()
```
    Create a GaussianReconstructionDistribution with the default identity activation function.
  - GaussianReconstructionDistribution
```
public GaussianReconstructionDistribution(Activation activationFn)
```
    Parameters:
    
    activationFn - Activation function for the reconstruction distribution. Typically identity or tanh.
  - GaussianReconstructionDistribution
```
public GaussianReconstructionDistribution(IActivation activationFn)
```
    Parameters:
    
    activationFn - Activation function for the reconstruction distribution. Typically identity or tanh.
- Method Detail
  - hasLossFunction
```
public boolean hasLossFunction()
```
    Description copied from interface: ReconstructionDistribution
    
    Does this reconstruction distribution has a standard neural network loss function (such as mean squared error, which is deterministic) or is it a standard VAE with a probabilistic reconstruction distribution?
    
    Specified by:
    
    hasLossFunction in interface ReconstructionDistribution
    
    Returns:
    
    true if the reconstruction distribution has a loss function only (and no probabilistic reconstruction distribution)
  - distributionInputSize
```
public int distributionInputSize(int dataSize)
```
    Description copied from interface: ReconstructionDistribution
    
    Get the number of distribution parameters for the given input data size. For example, a Gaussian distribution has 2 parameters value (mean and log(variance)) for each data value, whereas a Bernoulli distribution has only 1 parameter value (probability) for each data value.
    
    Specified by:
    
    distributionInputSize in interface ReconstructionDistribution
    
    Parameters:
    
    dataSize - Size of the data. i.e., nIn value
    
    Returns:
    
    Number of distribution parameters for the given reconstruction distribution
  - negLogProbability
```
public double negLogProbability(INDArray x,
                                INDArray preOutDistributionParams,
                                boolean average)
```
    Description copied from interface: ReconstructionDistribution
    
    Calculate the negative log probability (summed or averaged over each example in the minibatch)
    
    Specified by:
    
    negLogProbability in interface ReconstructionDistribution
    
    Parameters:
    
    x - Data to be modelled (reconstructions)
    
    preOutDistributionParams - Distribution parameters used by this reconstruction distribution (for example, mean and log variance values for Gaussian)
    
    average - Whether the log probability should be averaged over the minibatch, or simply summed.
    
    Returns:
    
    Average or sum of negative log probability of the reconstruction given the distribution parameters
  - exampleNegLogProbability
```
public INDArray exampleNegLogProbability(INDArray x,
                                         INDArray preOutDistributionParams)
```
    Description copied from interface: ReconstructionDistribution
    
    Calculate the negative log probability for each example individually
    
    Specified by:
    
    exampleNegLogProbability in interface ReconstructionDistribution
    
    Parameters:
    
    x - Data to be modelled (reconstructions)
    
    preOutDistributionParams - Distribution parameters used by this reconstruction distribution (for example, mean and log variance values for Gaussian) - before applying activation function
    
    Returns:
    
    Negative log probability of the reconstruction given the distribution parameters, for each example individually. Column vector, shape [numExamples, 1]
  - gradient
```
public INDArray gradient(INDArray x,
                         INDArray preOutDistributionParams)
```
    Description copied from interface: ReconstructionDistribution
    
    Calculate the gradient of the negative log probability with respect to the preOutDistributionParams
    
    Specified by:
    
    gradient in interface ReconstructionDistribution
    
    Parameters:
    
    x - Data
    
    preOutDistributionParams - Distribution parameters used by this reconstruction distribution (for example, mean and log variance values for Gaussian) - before applying activation function
    
    Returns:
    
    Gradient with respect to the preOutDistributionParams
  - generateRandom
```
public INDArray generateRandom(INDArray preOutDistributionParams)
```
    Description copied from interface: ReconstructionDistribution
    
    Randomly sample from P(x|z) using the specified distribution parameters
    
    Specified by:
    
    generateRandom in interface ReconstructionDistribution
    
    Parameters:
    
    preOutDistributionParams - Distribution parameters used by this reconstruction distribution (for example, mean and log variance values for Gaussian) - before applying activation function
    
    Returns:
    
    A random sample of x given the distribution parameters
  - generateAtMean
```
public INDArray generateAtMean(INDArray preOutDistributionParams)
```
    Description copied from interface: ReconstructionDistribution
    
    Generate a sample from P(x|z), where x = E[P(x|z)] i.e., return the mean value for the distribution
    
    Specified by:
    
    generateAtMean in interface ReconstructionDistribution
    
    Parameters:
    
    preOutDistributionParams - Distribution parameters used by this reconstruction distribution (for example, mean and log variance values for Gaussian) - before applying activation function
    
    Returns:
    
    A deterministic sample of x (mean/expected value) given the distribution parameters
  - toString
```
public String toString()
```
    Overrides:
    
    toString in class Object

Class GaussianReconstructionDistribution

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

GaussianReconstructionDistribution

GaussianReconstructionDistribution

GaussianReconstructionDistribution

Method Detail

hasLossFunction

distributionInputSize

negLogProbability

exampleNegLogProbability

gradient

generateRandom

generateAtMean

toString