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

Implementation of the MultiplyMerge module class. More...

#include <multiply_merge.hpp>

Public Member Functions
	MultiplyMerge (const bool model=false, const bool run=true)
	Create the MultiplyMerge object using the specified parameters. More...
	MultiplyMerge (const MultiplyMerge &layer)
	Copy Constructor.
	MultiplyMerge (MultiplyMerge &&layer)
	Move Constructor.
MultiplyMerge &	operator= (const MultiplyMerge &layer)
	Copy assignment operator.
MultiplyMerge &	operator= (MultiplyMerge &&layer)
	Move assignment operator.
	~MultiplyMerge ()
	Destructor to release allocated memory.
template<typename InputType , typename OutputType >
void	Forward (const InputType &, OutputType &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 trough f, using the results from the feed forward pass. More...
template<typename eT >
void	Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &error, arma::Mat< eT > &gradient)
template<class LayerType , class... Args>
void	Add (Args... args)
void	Add (LayerTypes< CustomLayers... > layer)
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.
std::vector< LayerTypes< CustomLayers... > > &	Model ()
	Return the model modules.
OutputDataType const &	Parameters () const
	Get the parameters.
OutputDataType &	Parameters ()
	Modify the parameters.
size_t	WeightSize () const
	Get the size of the weights.
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::MultiplyMerge< InputDataType, OutputDataType, CustomLayers >

Implementation of the MultiplyMerge module class.

The MultiplyMerge class multiplies the output of various modules element-wise.

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).
CustomLayers	Additional custom layers that can be added.

Constructor & Destructor Documentation

MultiplyMerge()

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

mlpack::ann::MultiplyMerge< InputDataType, OutputDataType, CustomLayers >::MultiplyMerge	(	const bool	model = false,
		const bool	run = true
	)

Create the MultiplyMerge object using the specified parameters.

Parameters

model	Expose all the network modules.
run	Call the Forward/Backward method before the output is merged.

Member Function Documentation

Backward()

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

template<typename eT >

void mlpack::ann::MultiplyMerge< 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 trough 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 InputType , typename OutputType >

void mlpack::ann::MultiplyMerge< InputDataType, OutputDataType, CustomLayers >::Forward	(	const InputType &	input,
		OutputType &	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.

---

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

• src/mlpack/methods/ann/layer/layer_types.hpp
• src/mlpack/methods/ann/layer/multiply_merge.hpp
• src/mlpack/methods/ann/layer/multiply_merge_impl.hpp