Implementation of the Reparametrization layer class. More...

Public Member Functions
	Reparametrization ()
	Create the Reparametrization object. More...

	Reparametrization (const size_t latentSize, const bool stochastic=true, const bool includeKl=true, const double beta=1)
	Create the Reparametrization layer object using the specified sample vector size. More...

	Reparametrization (const Reparametrization &layer)
	Copy Constructor. More...

	Reparametrization (Reparametrization &&layer)
	Move Constructor. More...

template < typename eT >
void	Backward (const arma::Mat< eT > &input, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. More...

double	Beta () const
	Get the value of the beta hyperparameter. More...

OutputDataType const &	Delta () const
	Get the delta. More...

OutputDataType &	Delta ()
	Modify the delta. More...

template < typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

bool	IncludeKL () const
	Get the value of the includeKl parameter. More...

size_t	InputShape () const

double	Loss ()
	Get the KL divergence with standard normal. More...

Reparametrization &	operator= (const Reparametrization &layer)
	Copy assignment operator. More...

Reparametrization &	operator= (Reparametrization &&layer)
	Move assignment operator. More...

OutputDataType const &	OutputParameter () const
	Get the output parameter. More...

OutputDataType &	OutputParameter ()
	Modify the output parameter. More...

size_t const &	OutputSize () const
	Get the output size. More...

size_t &	OutputSize ()
	Modify the output size. More...

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer. More...

bool	Stochastic () const
	Get the value of the stochastic parameter. More...

Detailed Description

template
<
typename
InputDataType
=
arma::mat
,
typename
OutputDataType
=
arma::mat
>

class mlpack::ann::Reparametrization< InputDataType, OutputDataType >

Implementation of the Reparametrization layer class.

This layer samples from the given parameters of a normal distribution.

This class also supports beta-VAE, a state-of-the-art framework for automated discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner.

For more information, refer the following paper.

@article{ICLR2017,
  title   = {beta-VAE: Learning basic visual concepts with a constrained
             variational framework},
  author  = {Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess,
             Xavier Glorot, Matthew Botvinick, Shakir Mohamed and
             Alexander Lerchner | Google DeepMind},
  journal = {2017 International Conference on Learning Representations(ICLR)},
  year    = {2017},
  url     = {https://deepmind.com/research/publications/beta-VAE-Learning-Basic-Visual-Concepts-with-a-Constrained-Variational-Framework}
}

Template Parameters

InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Definition at line 134 of file layer_types.hpp.

Constructor & Destructor Documentation

◆ Reparametrization() [1/4]

Reparametrization ( )

Create the Reparametrization object.

◆ Reparametrization() [2/4]

Reparametrization	(	const size_t	latentSize,
		const bool	stochastic = `true`,
		const bool	includeKl = `true`,
		const double	beta = `1`
	)

Create the Reparametrization layer object using the specified sample vector size.

Parameters

latentSize	The number of output latent units.
stochastic	Whether we want random sample or constant.
includeKl	Whether we want to include KL loss in backward function.
beta	The beta (hyper)parameter for beta-VAE mentioned above.

◆ Reparametrization() [3/4]

Reparametrization ( const Reparametrization< InputDataType, OutputDataType > & layer )

Copy Constructor.

◆ Reparametrization() [4/4]

Reparametrization ( Reparametrization< InputDataType, OutputDataType > && layer )

Move Constructor.

Member Function Documentation

◆ Backward()

void Backward	(	const arma::Mat< eT > &	input,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f.

Using the results from the feed forward pass.

Parameters

input	The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.

◆ Beta()

double Beta ( ) const

inline

Get the value of the beta hyperparameter.

Definition at line 143 of file reparametrization.hpp.

◆ Delta() [1/2]

OutputDataType const& Delta ( ) const

inline

Get the delta.

Definition at line 117 of file reparametrization.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 119 of file reparametrization.hpp.

◆ Forward()

void Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters

input	Input data used for evaluating the specified function.
output	Resulting output activation.

◆ IncludeKL()

bool IncludeKL ( ) const

inline

Get the value of the includeKl parameter.

Definition at line 140 of file reparametrization.hpp.

◆ InputShape()

size_t InputShape ( ) const

inline

Definition at line 145 of file reparametrization.hpp.

References Reparametrization< InputDataType, OutputDataType >::serialize().

◆ Loss()

double Loss ( )

inline

Get the KL divergence with standard normal.

Definition at line 127 of file reparametrization.hpp.

◆ operator=() [1/2]

Reparametrization& operator= ( const Reparametrization< InputDataType, OutputDataType > & layer )

Copy assignment operator.

◆ operator=() [2/2]

Reparametrization& operator= ( Reparametrization< InputDataType, OutputDataType > && layer )

Move assignment operator.

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 112 of file reparametrization.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 114 of file reparametrization.hpp.

◆ OutputSize() [1/2]

size_t const& OutputSize ( ) const

inline

Get the output size.

Definition at line 122 of file reparametrization.hpp.

◆ OutputSize() [2/2]

size_t& OutputSize ( )

inline

Modify the output size.

Definition at line 124 of file reparametrization.hpp.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by Reparametrization< InputDataType, OutputDataType >::InputShape().

◆ Stochastic()

bool Stochastic ( ) const

inline

Get the value of the stochastic parameter.

Definition at line 137 of file reparametrization.hpp.

The documentation for this class was generated from the following files:

/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/layer_types.hpp
/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/reparametrization.hpp

Public Member Functions

Detailed Description

template<typenameInputDataType=arma::mat,typenameOutputDataType=arma::mat> class mlpack::ann::Reparametrization< InputDataType, OutputDataType >

Constructor & Destructor Documentation

◆ Reparametrization() [1/4]

◆ Reparametrization() [2/4]

◆ Reparametrization() [3/4]

◆ Reparametrization() [4/4]

Member Function Documentation

◆ Backward()

◆ Beta()

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Forward()

◆ IncludeKL()

◆ InputShape()

◆ Loss()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ OutputParameter() [1/2]

◆ OutputParameter() [2/2]

◆ OutputSize() [1/2]

◆ OutputSize() [2/2]

◆ serialize()

◆ Stochastic()

template
<
typename
InputDataType
=
arma::mat
,
typename
OutputDataType
=
arma::mat
>

class mlpack::ann::Reparametrization< InputDataType, OutputDataType >