SHOGUN  v1.1.0
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages
List of all members | Public Member Functions
MKLMultiClassOptimizationBase Class Reference

Detailed Description

MKLMultiClassOptimizationBase is a helper class for MKLMultiClass.

it is a virtual base class for MKLMultiClassGLPK and MKLMultiClassGradient which are instances of optimization

Definition at line 25 of file MKLMultiClassOptimizationBase.h.

Inheritance diagram for MKLMultiClassOptimizationBase:
Inheritance graph
[legend]

Public Member Functions

 MKLMultiClassOptimizationBase ()
virtual ~MKLMultiClassOptimizationBase ()
virtual void setup (const int32_t numkernels2)
virtual void addconstraint (const ::std::vector< float64_t > &normw2, const float64_t sumofpositivealphas)
virtual void computeweights (std::vector< float64_t > &weights2)
virtual const char * get_name () const
virtual void set_mkl_norm (float64_t norm)
- Public Member Functions inherited from CSGObject
 CSGObject ()
 CSGObject (const CSGObject &orig)
virtual ~CSGObject ()
virtual bool is_generic (EPrimitiveType *generic) const
template<class T >
void set_generic ()
void unset_generic ()
virtual void print_serializable (const char *prefix="")
virtual bool save_serializable (CSerializableFile *file, const char *prefix="")
virtual bool load_serializable (CSerializableFile *file, const char *prefix="")
void set_global_io (SGIO *io)
SGIOget_global_io ()
void set_global_parallel (Parallel *parallel)
Parallelget_global_parallel ()
void set_global_version (Version *version)
Versionget_global_version ()
SGVector< char * > get_modelsel_names ()
char * get_modsel_param_descr (const char *param_name)
index_t get_modsel_param_index (const char *param_name)

Additional Inherited Members

- Public Attributes inherited from CSGObject
SGIOio
Parallelparallel
Versionversion
Parameterm_parameters
Parameterm_model_selection_parameters
- Protected Member Functions inherited from CSGObject
virtual void load_serializable_pre () throw (ShogunException)
virtual void load_serializable_post () throw (ShogunException)
virtual void save_serializable_pre () throw (ShogunException)
virtual void save_serializable_post () throw (ShogunException)

Constructor & Destructor Documentation

Class default Constructor

Definition at line 15 of file MKLMultiClassOptimizationBase.cpp.

Class default Destructor

Definition at line 19 of file MKLMultiClassOptimizationBase.cpp.

Member Function Documentation

void addconstraint ( const ::std::vector< float64_t > &  normw2,
const float64_t  sumofpositivealphas 
)
virtual

adds a constraint to the LP arising in L1 MKL based on two parameters

Parameters
normw2is the vector of $ \|w_k \|^2 $ for all kernels
sumofpositivealphasis a term depending on alphas, labels and biases, see in the function float64_t getsumofsignfreealphas() from MKLMultiClass.h, it depends on the formulation of the underlying GMNPSVM.

Reimplemented in MKLMultiClassGradient, and MKLMultiClassGLPK.

Definition at line 38 of file MKLMultiClassOptimizationBase.cpp.

void computeweights ( std::vector< float64_t > &  weights2)
virtual

computes MKL weights

Parameters
weights2stores the new weights

Reimplemented in MKLMultiClassGradient, and MKLMultiClassGLPK.

Definition at line 47 of file MKLMultiClassOptimizationBase.cpp.

virtual const char* get_name ( ) const
virtual
Returns
object name

Implements CSGObject.

Reimplemented in MKLMultiClassGradient, and MKLMultiClassGLPK.

Definition at line 64 of file MKLMultiClassOptimizationBase.h.

void set_mkl_norm ( float64_t  norm)
virtual

sets p-norm parameter for MKL

Parameters
normthe MKL norm

Reimplemented in MKLMultiClassGradient.

Definition at line 32 of file MKLMultiClassOptimizationBase.cpp.

void setup ( const int32_t  numkernels2)
virtual

initializes solver

Parameters
numkernels2is the number of kernels

Reimplemented in MKLMultiClassGradient, and MKLMultiClassGLPK.

Definition at line 26 of file MKLMultiClassOptimizationBase.cpp.


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

SHOGUN Machine Learning Toolbox - Documentation