mlpack::ann::NguyenWidrowInitialization Class Reference

This class is used to initialize the weight matrix with the Nguyen-Widrow method. More...

#include <nguyen_widrow_init.hpp>

Public Member Functions
	NguyenWidrowInitialization (const double lowerBound=-0.5, const double upperBound=0.5)
	Initialize the random initialization rule with the given lower bound and upper bound. More...
template<typename eT >
void	Initialize (arma::Mat< eT > &W, const size_t rows, const size_t cols)
	Initialize the elements of the specified weight matrix with the Nguyen-Widrow method. More...
template<typename eT >
void	Initialize (arma::Mat< eT > &W)
	Initialize the elements of the specified weight matrix with the Nguyen-Widrow 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 the Nguyen-Widrow method. More...
template<typename eT >
void	Initialize (arma::Cube< eT > &W)
	Initialize the elements of the specified weight 3rd order tensor with the Nguyen-Widrow method. More...

Detailed Description

This class is used to initialize the weight matrix with the Nguyen-Widrow method.

The method is defined by

\begin{eqnarray*} \gamma &\le& w_i \le \gamma \\ \beta &=& 0.7H^{\frac{1}{I}} \\ n &=& \sqrt{\sum_{i=0}{I}w_{i}^{2}} \\ w_i &=& \frac{\beta w_i}{n} \end{eqnarray*}

Where H is the number of neurons in the outgoing layer, I represents the number of neurons in the ingoing layer and gamma defines the random interval that is used to initialize the weights with a random value in a specific range.

Constructor & Destructor Documentation

NguyenWidrowInitialization()

mlpack::ann::NguyenWidrowInitialization::NguyenWidrowInitialization ( const double  lowerBound = -0.5, const double  upperBound = 0.5  )

inline

Initialize the random initialization rule with the given lower bound and upper bound.

Parameters

lowerBound	The number used as lower bound.
upperBound	The number used as upper bound.

Member Function Documentation

Initialize() [1/4]

template<typename eT >

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

inline

Initialize the elements of the specified weight matrix with the Nguyen-Widrow method.

Parameters

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

Initialize() [2/4]

template<typename eT >

void mlpack::ann::NguyenWidrowInitialization::Initialize ( arma::Mat< eT > &  W )

inline

Initialize the elements of the specified weight matrix with the Nguyen-Widrow method.

Parameters

W	Weight matrix to initialize.

Initialize() [3/4]

template<typename eT >

void mlpack::ann::NguyenWidrowInitialization::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 the Nguyen-Widrow method.

Parameters

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

Initialize() [4/4]

template<typename eT >

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

inline

Initialize the elements of the specified weight 3rd order tensor with the Nguyen-Widrow method.

Parameters

W	Weight matrix to initialize.

---

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

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