This class implements the Recurrent Model for Visual Attention, using a variety of possible layer implementations. More...

Public Member Functions
	RecurrentAttention ()
	Default constructor: this will not give a usable RecurrentAttention object, so be sure to set all the parameters before use. More...

template < typename RNNModuleType , typename ActionModuleType >
	RecurrentAttention (const size_t outSize, const RNNModuleType &rnn, const ActionModuleType &action, const size_t rho)
	Create the RecurrentAttention object using the specified modules. More...

template < typename eT >
void	Backward (const arma::Mat< eT > &, 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...

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

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

bool	Deterministic () const
	The value of the deterministic parameter. More...

bool &	Deterministic ()
	Modify the value of the deterministic parameter. 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...

template < typename eT >
void	Gradient (const arma::Mat< eT > &, const arma::Mat< eT > &, arma::Mat< eT > &)

OutputDataType const &	Gradient () const
	Get the gradient. More...

OutputDataType &	Gradient ()
	Modify the gradient. More...

std::vector< LayerTypes<> > &	Model ()
	Get the model modules. More...

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

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

size_t	OutSize () const
	Get the module output size. More...

OutputDataType const &	Parameters () const
	Get the parameters. More...

OutputDataType &	Parameters ()
	Modify the parameters. More...

size_t const &	Rho () const
	Get the number of steps to backpropagate through time. More...

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

Detailed Description

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

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

This class implements the Recurrent Model for Visual Attention, using a variety of possible layer implementations.

For more information, see the following paper.

@article{MnihHGK14,
  title   = {Recurrent Models of Visual Attention},
  author  = {Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu},
  journal = {CoRR},
  volume  = {abs/1406.6247},
  year    = {2014},
  url     = {https://arxiv.org/abs/1406.6247}
}

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 205 of file layer_types.hpp.

Constructor & Destructor Documentation

◆ RecurrentAttention() [1/2]

RecurrentAttention ( )

Default constructor: this will not give a usable RecurrentAttention object, so be sure to set all the parameters before use.

◆ RecurrentAttention() [2/2]

RecurrentAttention	(	const size_t	outSize,
		const RNNModuleType &	rnn,
		const ActionModuleType &	action,
		const size_t	rho
	)

Create the RecurrentAttention object using the specified modules.

Parameters

outSize	The module output size.
rnn	The recurrent neural network module.
action	The action module.
rho	Maximum number of steps to backpropagate through time (BPTT).

Member Function Documentation

◆ Backward()

void Backward	(	const arma::Mat< eT > &	,
		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.

◆ Delta() [1/2]

OutputDataType const& Delta ( ) const

inline

Get the delta.

Definition at line 133 of file recurrent_attention.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 135 of file recurrent_attention.hpp.

◆ Deterministic() [1/2]

bool Deterministic ( ) const

inline

The value of the deterministic parameter.

Definition at line 118 of file recurrent_attention.hpp.

◆ Deterministic() [2/2]

bool& Deterministic ( )

inline

Modify the value of the deterministic parameter.

Definition at line 120 of file recurrent_attention.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.

◆ Gradient() [1/3]

void Gradient	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	,
		arma::Mat< eT > &
	)

◆ Gradient() [2/3]

OutputDataType const& Gradient ( ) const

inline

Get the gradient.

Definition at line 138 of file recurrent_attention.hpp.

◆ Gradient() [3/3]

OutputDataType& Gradient ( )

inline

Modify the gradient.

Definition at line 140 of file recurrent_attention.hpp.

◆ Model()

std::vector<LayerTypes<> >& Model ( )

inline

Get the model modules.

Definition at line 115 of file recurrent_attention.hpp.

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 128 of file recurrent_attention.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 130 of file recurrent_attention.hpp.

◆ OutSize()

size_t OutSize ( ) const

inline

Get the module output size.

Definition at line 143 of file recurrent_attention.hpp.

◆ Parameters() [1/2]

OutputDataType const& Parameters ( ) const

inline

Get the parameters.

Definition at line 123 of file recurrent_attention.hpp.

◆ Parameters() [2/2]

OutputDataType& Parameters ( )

inline

Modify the parameters.

Definition at line 125 of file recurrent_attention.hpp.

◆ Rho()

size_t const& Rho ( ) const

inline

Get the number of steps to backpropagate through time.

Definition at line 146 of file recurrent_attention.hpp.

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

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by RecurrentAttention< InputDataType, OutputDataType >::Rho().

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/recurrent_attention.hpp

Public Member Functions

Detailed Description

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

Constructor & Destructor Documentation

◆ RecurrentAttention() [1/2]

◆ RecurrentAttention() [2/2]

Member Function Documentation

◆ Backward()

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Deterministic() [1/2]

◆ Deterministic() [2/2]

◆ Forward()

◆ Gradient() [1/3]

◆ Gradient() [2/3]

◆ Gradient() [3/3]

◆ Model()

◆ OutputParameter() [1/2]

◆ OutputParameter() [2/2]

◆ OutSize()

◆ Parameters() [1/2]

◆ Parameters() [2/2]

◆ Rho()

◆ serialize()

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

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