This class is used to initialize the weight matrix with the Glorot Initialization method. More...

Public Member Functions
	GlorotInitializationType ()
	Initialize the Glorot initialization object. More...

template<typename eT >
void	Initialize (arma::Mat< eT > &W, const size_t rows, const size_t cols)
	Initialize the elements weight matrix with glorot initialization method. More...

template<typename eT >
void	Initialize (arma::Cube< eT > &W, const size_t rows, const size_t cols, const size_t slices)
	Initialize the elements of the specified weight 3rd order tensor with glorot initialization method. More...

template<>
void	Initialize (arma::Mat< eT > &W, const size_t rows, const size_t cols)

template<>
void	Initialize (arma::Mat< eT > &W, const size_t rows, const size_t cols)

Detailed Description

template<bool Uniform = true>
class mlpack::ann::GlorotInitializationType< Uniform >

This class is used to initialize the weight matrix with the Glorot Initialization method.

The method is defined by

$\begin{eqnarray*} \mathrm{Var}[w_i] &=& \frac{2}{n_i + n_{i+1}} \\ w_i \sim \mathrm{U}[-\frac{\sqrt{6}}{\sqrt{n_i + n_{i+1}}}, \frac{\sqrt{6}}{\sqrt{n_i + n_{i+1}}}] \end{eqnarray*}$

where $n_{i+1}$ is the number of neurons in the outgoing layer, $ n_i $ represents the number of neurons in the ingoing layer. Here Normal Distribution may also be used if needed

For more information, see the following paper.

* @inproceedings {pmlr-v9-glorot10a,
*  title     = {Understanding the difficulty of training
*               deep feedforward neural networks},
*  author    = {Xavier Glorot and Yoshua Bengio},
*  booktitle = {Proceedings of the Thirteenth International Conference
*               on Artificial Intelligence and Statistics},
*  year      = {2010}
* }
* 

Definition at line 55 of file glorot_init.hpp.

Constructor & Destructor Documentation

GlorotInitializationType ( )

inline

Initialize the Glorot initialization object.

Definition at line 61 of file glorot_init.hpp.

Member Function Documentation

void Initialize	(	arma::Mat< eT > &	W,
		const size_t	rows,
		const size_t	cols
	)

Initialize the elements weight matrix with glorot initialization method.

Parameters

W	Weight matrix to initialize.
rows	Number of rows.
cols	Number of columns.

void Initialize	(	arma::Cube< eT > &	W,
		const size_t	rows,
		const size_t	cols,
		const size_t	slices
	)

inline

Initialize the elements of the specified weight 3rd order tensor with glorot initialization method.

Parameters

W	Weight matrix to initialize.
rows	Number of rows.
cols	Number of columns.
slice	Numbers of slices.

Definition at line 125 of file glorot_init.hpp.

void Initialize	(	arma::Mat< eT > &	W,
		const size_t	rows,
		const size_t	cols
	)

inline

Definition at line 96 of file glorot_init.hpp.

References GaussianInitialization::Initialize().

void Initialize	(	arma::Mat< eT > &	W,
		const size_t	rows,
		const size_t	cols
	)

inline

Definition at line 110 of file glorot_init.hpp.

References RandomInitialization::Initialize().

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

src/mlpack/methods/ann/init_rules/glorot_init.hpp

Public Member Functions

Detailed Description

template<bool Uniform = true> class mlpack::ann::GlorotInitializationType< Uniform >

Constructor & Destructor Documentation

Member Function Documentation

template<bool Uniform = true>
class mlpack::ann::GlorotInitializationType< Uniform >