OpenNN::ModelSelection Class Reference

#include <model_selection.h>

List of all members.

Classes

struct  ModelSelectionResults

Public Member Functions

 ModelSelection (void)
 ModelSelection (TrainingStrategy *)
 ModelSelection (const std::string &)
virtual ~ModelSelection (void)
TrainingStrategyget_training_strategy_pointer (void) const
const Vector< unsigned int > & get_hidden_perceptrons_numbers (void) const
const unsigned int & get_parameters_assays_number (void) const
const bool & get_reserve_parameters_data (void)
const bool & get_reserve_evaluation_data (void)
const bool & get_reserve_generalization_evaluation_data (void)
const bool & get_reserve_minimal_parameters (void)
const bool & get_reserve_evaluation_data_statistics (void)
const bool & get_reserve_generalization_evaluation_data_statistics (void)
const bool & get_reserve_model_order_selection_plot (void)
const bool & get_display (void) const
void set_training_strategy_pointer (TrainingStrategy *)
void set_default (void)
void set_hidden_perceptrons_numbers (const Vector< unsigned int > &)
void set_parameters_assays_number (const unsigned int &)
void set_assays_numbers (const unsigned int &, const unsigned int &)
void set_reserve_parameters_data (const bool &)
void set_reserve_evaluation_data (const bool &)
void set_reserve_generalization_evaluation_data (const bool &)
void set_reserve_minimal_parameters (const bool &)
void set_reserve_evaluation_data_statistics (const bool &)
void set_reserve_generalization_evaluation_data_statistics (const bool &)
void set_reserve_model_order_selection_plot (const bool &)
void set_display (const bool &)
void check (void) const
ModelSelectionResults perform_model_inputs_selection (void) const
ModelSelectionResults perform_model_order_selection (void) const
ModelSelectionResults perform_model_selection (void) const
TiXmlElement * to_XML (void) const
void from_XML (TiXmlElement *)
void print (void) const
void save (const std::string &) const
void load (const std::string &)


Detailed Description

This class represents the concept of model selection algorithm. It is used for finding a network architecture with maximum generalization capabilities.

Definition at line 35 of file model_selection.h.


Constructor & Destructor Documentation

OpenNN::ModelSelection::ModelSelection ( void   )  [explicit]

Default constructor.

Definition at line 39 of file model_selection.cpp.

OpenNN::ModelSelection::ModelSelection ( TrainingStrategy new_training_strategy_pointer  )  [explicit]

Training strategy constructor.

Parameters:
new_training_strategy_pointer Pointer to a gradient descent object.

Definition at line 51 of file model_selection.cpp.

OpenNN::ModelSelection::ModelSelection ( const std::string &  filename  )  [explicit]

File constructor.

Parameters:
filename Name of XML model selection file.

Definition at line 63 of file model_selection.cpp.

OpenNN::ModelSelection::~ModelSelection ( void   )  [virtual]

Destructor.

Definition at line 74 of file model_selection.cpp.


Member Function Documentation

TrainingStrategy * OpenNN::ModelSelection::get_training_strategy_pointer ( void   )  const

This method returns a pointer to the training strategy object.

Definition at line 85 of file model_selection.cpp.

const Vector< unsigned int > & OpenNN::ModelSelection::get_hidden_perceptrons_numbers ( void   )  const

This method returns the complexities of the neural networks given by the numbers of hidden perceptrons.

Definition at line 95 of file model_selection.cpp.

const unsigned int & OpenNN::ModelSelection::get_parameters_assays_number ( void   )  const

This method returns the number of trials for each network architecture.

Definition at line 105 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_parameters_data ( void   ) 

This method returns true if the neural network parameters are to be reserved, and false otherwise.

Definition at line 115 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_evaluation_data ( void   ) 

This method returns true if the performance functional evaluations are to be reserved, and false otherwise.

Definition at line 125 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_generalization_evaluation_data ( void   ) 

This method returns true if the performance functional generalization evaluations are to be reserved, and false otherwise.

Definition at line 135 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_minimal_parameters ( void   ) 

This method returns true if the parameters vector of the neural network with minimum performance functional evaluation is to be reserved, and false otherwise.

Definition at line 145 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_evaluation_data_statistics ( void   ) 

This method returns true if the statistics of the evaluation data are to be inclued in the model selection results.

Definition at line 155 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_generalization_evaluation_data_statistics ( void   ) 

This method returns true if the statistics of the generalization evaluation data are to be inclued in the model selection results.

Definition at line 165 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_reserve_model_order_selection_plot ( void   ) 

This method returns true if the necessary data for plotting the model selection results is to be included in the results.

Definition at line 175 of file model_selection.cpp.

const bool & OpenNN::ModelSelection::get_display ( void   )  const

This method returns true if messages from this class can be displayed on the screen, or false if messages from this class can't be displayed on the screen.

Definition at line 186 of file model_selection.cpp.

void OpenNN::ModelSelection::set_training_strategy_pointer ( TrainingStrategy new_training_strategy_pointer  ) 

This method sets a new training strategy pointer.

Parameters:
new_training_strategy_pointer Pointer to a training strategy object.

Definition at line 197 of file model_selection.cpp.

void OpenNN::ModelSelection::set_default ( void   ) 

Todo:

Definition at line 207 of file model_selection.cpp.

void OpenNN::ModelSelection::set_hidden_perceptrons_numbers ( const Vector< unsigned int > &  new_hidden_perceptrons_numbers  ) 

This method sets the number of complexities to be compared in the model order selection process.

Parameters:
new_hidden_perceptrons_numbers Vector with different hidden layers sizes.

Definition at line 220 of file model_selection.cpp.

void OpenNN::ModelSelection::set_parameters_assays_number ( const unsigned int &  new_parameters_assays_number  ) 

This method sets the number of times that each different neural network is to be trained.

Parameters:
new_parameters_assays_number Number of assays for each set of parameters.

Definition at line 231 of file model_selection.cpp.

void OpenNN::ModelSelection::set_assays_numbers ( const unsigned int &  new_complexity_assays_number,
const unsigned int &  new_parameters_assays_number 
)

This method sets the numbers of complexities and assays.

Parameters:
new_complexity_assays_number Number of hidden neurons.
new_parameters_assays_number Number of trainings for each different neural network.

Definition at line 243 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_parameters_data ( const bool &  new_reserve_parameters_data  ) 

This method sets the reserve flag for the parameters data.

Parameters:
new_reserve_parameters_data Flag value.

Definition at line 317 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_evaluation_data ( const bool &  new_reserve_evaluation_data  ) 

This method sets the reserve flag for the evaluation data.

Parameters:
new_reserve_evaluation_data Flag value.

Definition at line 328 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_generalization_evaluation_data ( const bool &  new_reserve_generalization_evaluation_data  ) 

This method sets the reserve flag for the generalization evaluation data.

Parameters:
new_reserve_generalization_evaluation_data Flag value.

Definition at line 339 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_minimal_parameters ( const bool &  new_reserve_minimal_parameters  ) 

This method sets the reserve flag for the minimal parameters.

Parameters:
new_reserve_minimal_parameters Flag value.

Definition at line 350 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_evaluation_data_statistics ( const bool &  new_reserve_evaluation_data_statistics  ) 

This method sets the reserve flag for the evaluation data statistics.

Parameters:
new_reserve_evaluation_data_statistics Flag value.

Definition at line 361 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_generalization_evaluation_data_statistics ( const bool &  new_reserve_generalization_evaluation_data_statistics  ) 

This method sets the reserve flag for the generalization evaluation data statistics.

Parameters:
new_reserve_generalization_evaluation_data_statistics Flag value.

Definition at line 372 of file model_selection.cpp.

void OpenNN::ModelSelection::set_reserve_model_order_selection_plot ( const bool &  new_reserve_model_order_selection_plot  ) 

This method sets the reserve flag for the model order selection plot.

Parameters:
new_reserve_model_order_selection_plot Flag value.

Definition at line 383 of file model_selection.cpp.

void OpenNN::ModelSelection::set_display ( const bool &  new_display  ) 

This method sets a new display value. If it is set to true messages from this class are to be displayed on the screen; if it is set to false messages from this class are not to be displayed on the screen.

Parameters:
new_display Display value.

Definition at line 396 of file model_selection.cpp.

void OpenNN::ModelSelection::check ( void   )  const

This method checks that the different pointers needed for performing the model selection are not NULL.

Definition at line 406 of file model_selection.cpp.

ModelSelection::ModelSelectionResults OpenNN::ModelSelection::perform_model_inputs_selection ( void   )  const

Todo:

Definition at line 465 of file model_selection.cpp.

ModelSelection::ModelSelectionResults OpenNN::ModelSelection::perform_model_order_selection ( void   )  const

Todo:

Definition at line 587 of file model_selection.cpp.

ModelSelection::ModelSelectionResults OpenNN::ModelSelection::perform_model_selection ( void   )  const

Todo:

Definition at line 781 of file model_selection.cpp.

TiXmlElement * OpenNN::ModelSelection::to_XML ( void   )  const

This method serializes the model selection object into a XML element of the TinyXML library. See the OpenNN manual for more information about the format of this element.

Definition at line 802 of file model_selection.cpp.

void OpenNN::ModelSelection::from_XML ( TiXmlElement *   ) 

Todo:

Definition at line 841 of file model_selection.cpp.

void OpenNN::ModelSelection::print ( void   )  const

This method prints to the screen the XML representation of this model selection object.

Definition at line 850 of file model_selection.cpp.

void OpenNN::ModelSelection::save ( const std::string &  filename  )  const

This method saves the model selection members to a XML file.

Parameters:
filename Name of model selection XML file.

Definition at line 861 of file model_selection.cpp.

void OpenNN::ModelSelection::load ( const std::string &  filename  ) 

This method loads the model selection members from a XML file.

Parameters:
filename Name of model selection XML file.

Definition at line 886 of file model_selection.cpp.


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

Generated on Sun Aug 26 11:58:17 2012 for OpenNN by  doxygen 1.5.9