mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers > Class Template Reference

Implementation of the Highway layer. More...

#include <highway.hpp>

Public Member Functions
	Highway ()
	Create the Highway object.
	Highway (const size_t inSize, const bool model=true)
	Create the Highway object. More...
	~Highway ()
	Destroy the Highway object.
void	Reset ()
	Reset the layer parameter.
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	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 through f. More...
template<typename eT >
void	Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &error, arma::Mat< eT > &gradient)
	Calculate the gradient using the output delta and the input activation. More...
template<class LayerType , class... Args>
void	Add (Args... args)
	Add a new module to the model. More...
void	Add (LayerTypes< CustomLayers... > layer)
	Add a new module to the model. More...
std::vector< LayerTypes< CustomLayers... > > &	Model ()
	Return the modules of the model.
OutputDataType const &	Parameters () const
	Get the parameters.
OutputDataType &	Parameters ()
	Modify the parameters.
InputDataType const &	InputParameter () const
	Get the input parameter.
InputDataType &	InputParameter ()
	Modify the input parameter.
OutputDataType const &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
OutputDataType const &	Delta () const
	Get the delta.
OutputDataType &	Delta ()
	Modify the delta.
OutputDataType const &	Gradient () const
	Get the gradient.
OutputDataType &	Gradient ()
	Modify the gradient.
size_t	InSize () const
	Get the number of input units.
size_t	InputShape () const
	Get the shape of the input.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, typename... CustomLayers>
class mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >

Implementation of the Highway layer.

The Highway class can vary its behavior between that of feed-forward fully connected network container and that of a layer which simply passes its inputs through depending on the transform gate. Note that the size of the input and output matrices of this class should be equal.

For more information, refer the following paper.

@article{Srivastava2015,
  author  = {Rupesh Kumar Srivastava, Klaus Greff, Jurgen Schmidhuber},
  title   = {Training Very Deep Networks},
  journal = {Advances in Neural Information Processing Systems},
  year    = {2015},
  url     = {https://arxiv.org/abs/1507.06228},
}

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).

Constructor & Destructor Documentation

Highway()

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >::Highway	(	const size_t	inSize,
		const bool	model = true
	)

Create the Highway object.

Parameters

inSize	The number of input units.
model	Expose all the network modules.

Member Function Documentation

Add() [1/2]

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

template<class LayerType , class... Args>

void mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >::Add ( Args...  args )

inline

Add a new module to the model.

Parameters

args	The layer parameter.

Add() [2/2]

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

void mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >::Add ( LayerTypes< CustomLayers... >  layer )

inline

Add a new module to the model.

Parameters

layer

The Layer to be added to the model.

Backward()

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

template<typename eT >

void mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >::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 through f.

Using the results from the feed-forward pass.

Parameters

*	(input) The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.

Forward()

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

template<typename eT >

void mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >::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()

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

template<typename eT >

void mlpack::ann::Highway< InputDataType, OutputDataType, CustomLayers >::Gradient	(	const arma::Mat< eT > &	input,
		const arma::Mat< eT > &	error,
		arma::Mat< eT > &	gradient
	)

Calculate the gradient using the output delta and the input activation.

Parameters

input	The input parameter used for calculating the gradient.
error	The calculated error.
gradient	The calculated gradient.

---

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

• src/mlpack/methods/ann/layer/highway.hpp
• src/mlpack/methods/ann/layer/highway_impl.hpp