mlpack::ann::GlorotInitializationType< Uniform > Class Template Reference

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

#include <glorot_init.hpp>

Public Member Functions
	GlorotInitializationType ()
	Initialize the Glorot initialization object.
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::Mat< eT > &W)
	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<typename eT >
void	Initialize (arma::Cube< eT > &W)
	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)
template<>
void	Initialize (arma::Mat< eT > &W, const size_t rows, const size_t cols)
template<>
void	Initialize (arma::Mat< eT > &W)

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}
}

Member Function Documentation

Initialize() [1/4]

template<bool Uniform = true>

template<typename eT >

void mlpack::ann::GlorotInitializationType< Uniform >::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.

Initialize() [2/4]

template<bool Uniform = true>

template<typename eT >

void mlpack::ann::GlorotInitializationType< Uniform >::Initialize

(

arma::Mat< eT > &

W

)

Initialize the elements weight matrix with glorot initialization method.

Parameters

W	Weight matrix to initialize.

Initialize() [3/4]

template<bool Uniform>

template<typename eT >

void mlpack::ann::GlorotInitializationType< Uniform >::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.
slices	Number of slices.

Initialize() [4/4]

template<bool Uniform>

template<typename eT >

void mlpack::ann::GlorotInitializationType< Uniform >::Initialize ( arma::Cube< eT > &  W )

inline

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

Parameters

W	Weight matrix to initialize.

---

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

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