shark::AbstractUnsupervisedTrainer< Model > Class Template Reference

Superclass of unsupervised learning algorithms. More...

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

Inheritance diagram for shark::AbstractUnsupervisedTrainer< Model >:

Public Types
typedef Model	ModelType
typedef Model::InputType	InputType
typedef UnlabeledData< InputType >	DatasetType

Public Member Functions
virtual void	train (ModelType &model, DatasetType const &inputset)=0
	Core of the Trainer interface.
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 shark::AbstractUnsupervisedTrainer< Model >

Superclass of unsupervised learning algorithms.

AbstractUnsupervisedTrainer is the superclass of all unsupervised learning algorithms. It consists of a single virtual function to train the model.

Note: Most learning algorithms of this type operate on a special model type, such as a linear model, a kernel expansion, or a nearest neighbor model. Thus, these algorithms should provide a specialized train method that accepts only this model type. The virtual train method should be overriden with a method that checks the type of the model and calls the specialized train method.

Definition at line 106 of file AbstractTrainer.h.

Member Typedef Documentation

DatasetType

template<class Model >

typedef UnlabeledData<InputType> shark::AbstractUnsupervisedTrainer< Model >::DatasetType

Definition at line 111 of file AbstractTrainer.h.

InputType

template<class Model >

typedef Model::InputType shark::AbstractUnsupervisedTrainer< Model >::InputType

Definition at line 110 of file AbstractTrainer.h.

ModelType

template<class Model >

typedef Model shark::AbstractUnsupervisedTrainer< Model >::ModelType

Definition at line 109 of file AbstractTrainer.h.

Member Function Documentation

train()

template<class Model >

virtual void shark::AbstractUnsupervisedTrainer< Model >::train ( ModelType &  model, DatasetType const &  inputset  )

pure virtual

Core of the Trainer interface.

Implemented in shark::AbstractWeightedUnsupervisedTrainer< Model >.

---

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

• include/shark/Algorithms/Trainers/AbstractTrainer.h