Implementation of the Radial Basis Function layer. More...

#include <radial_basis_function.hpp>

Public Member Functions
	RBF ()
	Create the RBF object.

	RBF (const size_t inSize, const size_t outSize, arma::mat &centres, double betas=0)
	Create the Radial Basis Function layer object using the specified parameters. More...

template<typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of the radial basis function. More...

template<typename eT >
void	Backward (const arma::Mat< eT > &, const arma::Mat< eT > &, arma::Mat< eT > &)
	Ordinary feed backward pass of the radial basis function.

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

OutputDataType &	OutputParameter ()
	Modify the output parameter.

InputDataType const &	InputParameter () const
	Get the parameters. More...

InputDataType &	InputParameter ()
	Modify the input parameter.

size_t	InputSize () const
	Get the input size.

size_t	OutputSize () const
	Get the output size.

OutputDataType const &	Delta () const
	Get the detla.

OutputDataType &	Delta ()
	Modify the delta.

size_t	WeightSize () const
	Get the size of the weights.

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 Activation = GaussianFunction>
class mlpack::ann::RBF< InputDataType, OutputDataType, Activation >

Implementation of the Radial Basis Function layer.

The RBF class when use with a non-linear activation function acts as a Radial Basis Function which can be used with Feed-Forward neural network.

For more information, refer to the following paper,

@article{Volume 51: Artificial Intelligence and Statistics,
  author  = {Qichao Que, Mikhail Belkin},
  title   = {Back to the Future: Radial Basis Function Networks Revisited},
  year    = {2016},
  url     = {http://proceedings.mlr.press/v51/que16.pdf},
}

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).
Activation	Type of the activation function (mlpack::ann::Gaussian).

Constructor & Destructor Documentation

◆ RBF()

template<typename InputDataType , typename OutputDataType , typename Activation >

mlpack::ann::RBF< InputDataType, OutputDataType, Activation >::RBF	(	const size_t	inSize,
		const size_t	outSize,
		arma::mat &	centres,
		double	betas = `0`
	)

Create the Radial Basis Function layer object using the specified parameters.

Parameters

inSize	The number of input units.
outSize	The number of output units.
centres	The centres calculated using k-means of data.
betas	The beta value to be used with centres.

Member Function Documentation

◆ Forward()

template<typename InputDataType , typename OutputDataType , typename Activation >

template<typename eT >

void mlpack::ann::RBF< InputDataType, OutputDataType, Activation >::Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed forward pass of the radial basis function.

Parameters

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

◆ InputParameter()

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

InputDataType const& mlpack::ann::RBF< InputDataType, OutputDataType, Activation >::InputParameter ( ) const

inline

Get the parameters.

Get the input parameter.

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

src/mlpack/methods/ann/layer/layer_types.hpp
src/mlpack/methods/ann/layer/radial_basis_function.hpp
src/mlpack/methods/ann/layer/radial_basis_function_impl.hpp

Public Member Functions