Superclass of weighted supervised learning algorithms. More...

#include <shark/Algorithms/Trainers/AbstractWeightedTrainer.h>

Inheritance diagram for shark::AbstractWeightedTrainer< Model, LabelTypeT >:

Public Types
typedef base_type::ModelType	ModelType

typedef base_type::InputType	InputType

typedef base_type::LabelType	LabelType

typedef base_type::DatasetType	DatasetType

typedef WeightedLabeledData< InputType, LabelType >	WeightedDatasetType

Public Types inherited from shark::AbstractTrainer< Model, LabelTypeT >
typedef Model	ModelType

typedef ModelType::InputType	InputType

typedef LabelTypeT	LabelType

typedef LabeledData< InputType, LabelType >	DatasetType

Public Member Functions
virtual void	train (ModelType &model, WeightedDatasetType const &dataset)=0
	Executes the algorithm and trains a model on the given weighted data.

virtual void	train (ModelType &model, DatasetType const &dataset)
	Executes the algorithm and trains a model on the given unweighted data.

Public Member Functions inherited from shark::INameable
virtual	~INameable ()

virtual std::string	name () const
	returns the name of the object

Public Member Functions inherited from shark::ISerializable
virtual	~ISerializable ()
	Virtual d'tor.

virtual void	read (InArchive &archive)
	Read the component from the supplied archive.

virtual void	write (OutArchive &archive) const
	Write the component to the supplied archive.

void	load (InArchive &archive, unsigned int version)
	Versioned loading of components, calls read(...).

void	save (OutArchive &archive, unsigned int version) const
	Versioned storing of components, calls write(...).

	BOOST_SERIALIZATION_SPLIT_MEMBER ()

Detailed Description

template<class Model, class LabelTypeT = typename Model::OutputType>
class shark::AbstractWeightedTrainer< Model, LabelTypeT >

Superclass of weighted supervised learning algorithms.

: AbstractWeightedTrainer is the super class of all trainers that support weighted datasets. Weights are interpreted here as the importance of a sample. unweighted training assumes that all samples have the same importance, or weight. The higher the weight, the more important a point. Weight 0 is the same as if the point would not be part of the dataset. Negative weights are not allowed.

When all weights are integral values there is a simple interpretation of the weights as the multiplicity of a point. Thus training with a dataset with duplicate points is the same as counting the duplicates and run the algorithm with a weighted dataset where all points are unique and have their weight is the multiplicity.

Definition at line 61 of file AbstractWeightedTrainer.h.