mlpack::ann::CReLU< InputDataType, OutputDataType > Class Template Reference

A concatenated ReLU has two outputs, one ReLU and one negative ReLU, concatenated together. More...

#include <c_relu.hpp>

Public Member Functions
	CReLU ()
	Create the CReLU object.
template<typename InputType , typename OutputType >
void	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. More...
template<typename DataType >
void	Backward (const DataType &input, const DataType &gy, DataType &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...
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.
size_t	WeightSize () const
	Get size of weights.
template<typename Archive >
void	serialize (Archive &, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::CReLU< InputDataType, OutputDataType >

A concatenated ReLU has two outputs, one ReLU and one negative ReLU, concatenated together.

In other words, for positive x it produces [x, 0], and for negative x it produces [0, x]. Because it has two outputs, CReLU doubles the output dimension.

Note: The CReLU doubles the output size.

For more information, see the following.

@inproceedings{ICML2016,
  title  = {Understanding and Improving Convolutional Neural Networks
            via Concatenated Rectified Linear Units},
  author = {LWenling Shang, Kihyuk Sohn, Diogo Almeida, Honglak Lee},
  year   = {2016},
  url    = {https://arxiv.org/abs/1603.05201}
}

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).

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename DataType >

void mlpack::ann::CReLU< InputDataType, OutputDataType >::Backward	(	const DataType &	input,
		const DataType &	gy,
		DataType &	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 >

template<typename InputType , typename OutputType >

void mlpack::ann::CReLU< InputDataType, OutputDataType >::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.

Works only for 2D Tensors.

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/c_relu.hpp
• src/mlpack/methods/ann/layer/c_relu_impl.hpp