SHOGUN  4.2.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
List of all members | Public Types | Static Public Member Functions
softmax< Backend::EIGEN3, Matrix > Struct Template Reference

Detailed Description

template<class Matrix>
struct shogun::linalg::implementation::special_purpose::softmax< Backend::EIGEN3, Matrix >

Specialization of softmax for the Eigen3 backend

Definition at line 310 of file implementation/SpecialPurpose.h.

Public Types

typedef Matrix::Scalar T
 
typedef Eigen::Matrix< T,
Eigen::Dynamic, Eigen::Dynamic > 
MatrixXt
 

Static Public Member Functions

static void compute (SGMatrix< T > A)
 

Member Typedef Documentation

typedef Eigen::Matrix<T,Eigen::Dynamic,Eigen::Dynamic> MatrixXt

Eigen matrix type

Definition at line 316 of file implementation/SpecialPurpose.h.

typedef Matrix::Scalar T

Scalar type

Definition at line 313 of file implementation/SpecialPurpose.h.

Member Function Documentation

static void compute ( SGMatrix< T A)
static

Applies the softmax function inplace to a matrix. The softmax function is defined as \( f(A[i,j]) = \frac{exp(A[i,j])}{\sum_i exp(A[i,j])} \)

Definition at line 321 of file implementation/SpecialPurpose.h.


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

SHOGUN Machine Learning Toolbox - Documentation