OpenNN::LevenbergMarquardtAlgorithm Class Reference

#include <levenberg_marquardt_algorithm.h>

Inheritance diagram for OpenNN::LevenbergMarquardtAlgorithm:

OpenNN::TrainingAlgorithm

List of all members.

Classes

struct  LevenbergMarquardtAlgorithmResults

Public Member Functions

 LevenbergMarquardtAlgorithm (void)
 LevenbergMarquardtAlgorithm (PerformanceFunctional *)
 LevenbergMarquardtAlgorithm (TiXmlElement *)
virtual ~LevenbergMarquardtAlgorithm (void)
const double & get_warning_parameters_norm (void) const
const double & get_warning_gradient_norm (void) const
const double & get_error_parameters_norm (void) const
const double & get_error_gradient_norm (void) const
const double & get_minimum_parameters_increment_norm (void) const
const double & get_minimum_performance_increase (void) const
const double & get_performance_goal (void) const
const double & get_gradient_norm_goal (void) const
const unsigned int & get_maximum_generalization_evaluation_decreases (void) const
const unsigned int & get_maximum_epochs_number (void) const
const double & get_maximum_time (void) const
const bool & get_reserve_parameters_history (void) const
const bool & get_reserve_parameters_norm_history (void) const
const bool & get_reserve_evaluation_history (void) const
const bool & get_reserve_gradient_history (void) const
const bool & get_reserve_gradient_norm_history (void) const
const bool & get_reserve_inverse_Hessian_history (void) const
const bool & get_reserve_generalization_evaluation_history (void) const
const bool & get_reserve_elapsed_time_history (void) const
const unsigned int & get_display_period (void) const
const double & get_damping_parameter (void) const
const double & get_damping_parameter_factor (void) const
const double & get_minimum_damping_parameter (void) const
const double & get_maximum_damping_parameter (void) const
const bool & get_reserve_damping_parameter_history (void) const
const Vector< double > & get_damping_parameter_history (void) const
void set_default (void)
void set_damping_parameter (const double &)
void set_damping_parameter_factor (const double &)
void set_minimum_damping_parameter (const double &)
void set_maximum_damping_parameter (const double &)
void set_reserve_damping_parameter_history (const bool &)
void set_warning_parameters_norm (const double &)
void set_warning_gradient_norm (const double &)
void set_error_parameters_norm (const double &)
void set_error_gradient_norm (const double &)
void set_minimum_parameters_increment_norm (const double &)
void set_minimum_performance_increase (const double &)
void set_performance_goal (const double &)
void set_gradient_norm_goal (const double &)
void set_maximum_generalization_evaluation_decreases (const unsigned int &)
void set_maximum_epochs_number (const unsigned int &)
void set_maximum_time (const double &)
void set_reserve_parameters_history (const bool &)
void set_reserve_parameters_norm_history (const bool &)
void set_reserve_evaluation_history (const bool &)
void set_reserve_gradient_history (const bool &)
void set_reserve_gradient_norm_history (const bool &)
void set_reserve_inverse_Hessian_history (const bool &)
void set_reserve_generalization_evaluation_history (const bool &)
void set_reserve_elapsed_time_history (const bool &)
virtual void set_reserve_all_training_history (const bool &)
void set_display_period (const unsigned int &)
void check (void) const
Vector< double > calculate_gradient (const Vector< double > &, const Matrix< double > &) const
Matrix< double > calculate_Hessian_approximation (const Matrix< double > &) const
LevenbergMarquardtAlgorithmResultsperform_training (void)
std::string write_training_algorithm_type (void) const
TiXmlElement * to_XML (void) const
void from_XML (TiXmlElement *)


Detailed Description

This concrete class represents a Levenberg-Marquardt Algorithm training algorithm for the sum squared error performance functional for a multilayer perceptron.

Definition at line 39 of file levenberg_marquardt_algorithm.h.


Constructor & Destructor Documentation

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

Default constructor. It creates a Levenberg-Marquardt training algorithm object not associated to any performance functional object. It also initializes the class members to their default values.

Definition at line 44 of file levenberg_marquardt_algorithm.cpp.

OpenNN::LevenbergMarquardtAlgorithm::LevenbergMarquardtAlgorithm ( PerformanceFunctional new_performance_functional_pointer  )  [explicit]

Performance functional constructor. It creates a Levenberg-Marquardt training algorithm object associated associated with a given performance functional object. It also initializes the class members to their default values.

Parameters:
new_performance_functional_pointer Pointer to an external performance functional object.

Definition at line 58 of file levenberg_marquardt_algorithm.cpp.

OpenNN::LevenbergMarquardtAlgorithm::LevenbergMarquardtAlgorithm ( TiXmlElement *  Levenberg_Marquardt_algorithm_element  )  [explicit]

XML Constructor. This method creates a Levenberg-Marquardt algorithm object, and loads its members from a XML element.

Parameters:
Levenberg_Marquardt_algorithm_element Pointer to a TinyXML element containing the Levenberg-Marquardt algorithm data.

Definition at line 71 of file levenberg_marquardt_algorithm.cpp.

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

Destructor. This destructor does not delete any object.

Definition at line 85 of file levenberg_marquardt_algorithm.cpp.


Member Function Documentation

const double & OpenNN::LevenbergMarquardtAlgorithm::get_warning_parameters_norm ( void   )  const

This method returns the minimum value for the norm of the parameters vector at wich a warning message is written to the screen.

Definition at line 95 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_warning_gradient_norm ( void   )  const

This method returns the minimum value for the norm of the gradient vector at wich a warning message is written to the screen.

Definition at line 106 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_error_parameters_norm ( void   )  const

This method returns the value for the norm of the parameters vector at wich an error message is written to the screen and the program exits.

Definition at line 117 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_error_gradient_norm ( void   )  const

This method returns the value for the norm of the gradient vector at wich an error message is written to the screen and the program exits.

Definition at line 128 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_minimum_parameters_increment_norm ( void   )  const

This method returns the minimum norm of the parameter increment vector used as a stopping criteria when training.

Definition at line 138 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_minimum_performance_increase ( void   )  const

This method returns the minimum performance improvement during training.

Definition at line 148 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_performance_goal ( void   )  const

This method returns the goal value for the performance. This is used as a stopping criterium when training a multilayer perceptron

Definition at line 159 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_gradient_norm_goal ( void   )  const

This method returns the goal value for the norm of the objective function gradient. This is used as a stopping criterium when training a multilayer perceptron

Definition at line 170 of file levenberg_marquardt_algorithm.cpp.

const unsigned int & OpenNN::LevenbergMarquardtAlgorithm::get_maximum_generalization_evaluation_decreases ( void   )  const

This method returns the maximum number of generalization failures during the training process.

Definition at line 180 of file levenberg_marquardt_algorithm.cpp.

const unsigned int & OpenNN::LevenbergMarquardtAlgorithm::get_maximum_epochs_number ( void   )  const

This method returns the maximum number of epochs for training.

Definition at line 190 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_maximum_time ( void   )  const

This method returns the maximum training time.

Definition at line 200 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_parameters_history ( void   )  const

This method returns true if the parameters history matrix is to be reserved, and false otherwise.

Definition at line 210 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_parameters_norm_history ( void   )  const

This method returns true if the parameters norm history vector is to be reserved, and false otherwise.

Definition at line 220 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_evaluation_history ( void   )  const

This method returns true if the evaluation history vector is to be reserved, and false otherwise.

Definition at line 230 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_gradient_history ( void   )  const

This method returns true if the gradient history vector of vectors is to be reserved, and false otherwise.

Definition at line 240 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_gradient_norm_history ( void   )  const

This method returns true if the gradient norm history vector is to be reserved, and false otherwise.

Definition at line 250 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_inverse_Hessian_history ( void   )  const

This method returns true if the inverse Hessian history vector of matrices is to be reserved, and false otherwise.

Definition at line 260 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_generalization_evaluation_history ( void   )  const

This method returns true if the Generalization evaluation history vector is to be reserved, and false otherwise.

Definition at line 280 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_elapsed_time_history ( void   )  const

This method returns true if the elapsed time history vector is to be reserved, and false otherwise.

Definition at line 270 of file levenberg_marquardt_algorithm.cpp.

const unsigned int & OpenNN::LevenbergMarquardtAlgorithm::get_display_period ( void   )  const

This method returns the number of epochs between the training showing progress.

Definition at line 290 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_damping_parameter ( void   )  const

This method returns the damping parameter for the Hessian approximation.

Definition at line 300 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_damping_parameter_factor ( void   )  const

This method returns the damping parameter factor (beta in the User's Guide) for the Hessian approximation.

Definition at line 310 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_minimum_damping_parameter ( void   )  const

This method returns the minimum damping parameter allowed in the algorithm.

Definition at line 320 of file levenberg_marquardt_algorithm.cpp.

const double & OpenNN::LevenbergMarquardtAlgorithm::get_maximum_damping_parameter ( void   )  const

This method returns the maximum damping parameter allowed in the algorithm.

Definition at line 330 of file levenberg_marquardt_algorithm.cpp.

const bool & OpenNN::LevenbergMarquardtAlgorithm::get_reserve_damping_parameter_history ( void   )  const

This method returns true if the damping parameter history vector is to be reserved, and false otherwise.

Definition at line 340 of file levenberg_marquardt_algorithm.cpp.

const Vector< double > & OpenNN::LevenbergMarquardtAlgorithm::get_damping_parameter_history ( void   )  const

This method returns a vector containing the damping parameter history over the training epochs.

Definition at line 350 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_default ( void   )  [virtual]

This method sets the following default values for the Levenberg-Marquardt algorithm: Training parameters:

  • Levenberg-Marquardt parameter: 0.001.
Stopping criteria:
  • Performance goal: 0.0.
  • Gradient approximation norm goal: 0.0.
  • Maximum training time: 1.0e6.
  • Maximum number of epochs: 100.
User stuff:
  • Epochs between showing progress: 10.

Reimplemented from OpenNN::TrainingAlgorithm.

Definition at line 375 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_damping_parameter ( const double &  new_damping_parameter  ) 

This method sets a new damping parameter (lambda in the User's Guide) for the Hessian approximation.

Parameters:
new_damping_parameter Damping parameter value.

Definition at line 432 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_damping_parameter_factor ( const double &  new_damping_parameter_factor  ) 

This method sets a new damping parameter factor (beta in the User's Guide) for the Hessian approximation.

Parameters:
new_damping_parameter_factor Damping parameter factor value.

Definition at line 454 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_minimum_damping_parameter ( const double &  new_minimum_damping_parameter  ) 

This method sets a new minimum damping parameter allowed in the algorithm.

Parameters:
new_minimum_damping_parameter Minimum damping parameter value.

Definition at line 480 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_maximum_damping_parameter ( const double &  new_maximum_damping_parameter  ) 

This method sets a new maximum damping parameter allowed in the algorithm.

Parameters:
new_maximum_damping_parameter Maximum damping parameter value.

Definition at line 506 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_damping_parameter_history ( const bool &  new_reserve_damping_parameter_history  ) 

This method makes the damping parameter history vector to be reseved or not in memory.

Parameters:
new_reserve_damping_parameter_history True if the damping parameter history vector is to be reserved, false otherwise.

Definition at line 532 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_warning_parameters_norm ( const double &  new_warning_parameters_norm  ) 

This method sets a new value for the parameters vector norm at which a warning message is written to the screen.

Parameters:
new_warning_parameters_norm Warning norm of parameters vector value.

Definition at line 544 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_warning_gradient_norm ( const double &  new_warning_gradient_norm  ) 

This method sets a new value for the gradient vector norm at which a warning message is written to the screen.

Parameters:
new_warning_gradient_norm Warning norm of gradient vector value.

Definition at line 575 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_error_parameters_norm ( const double &  new_error_parameters_norm  ) 

This method sets a new value for the parameters vector norm at which an error message is written to the screen and the program exits.

Parameters:
new_error_parameters_norm Error norm of parameters vector value.

Definition at line 606 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_error_gradient_norm ( const double &  new_error_gradient_norm  ) 

This method sets a new value for the gradient vector norm at which an error message is written to the screen and the program exits.

Parameters:
new_error_gradient_norm Error norm of gradient vector value.

Definition at line 637 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_minimum_parameters_increment_norm ( const double &  new_minimum_parameters_increment_norm  ) 

This method sets a new value for the minimum parameters increment norm stopping criterium.

Parameters:
new_minimum_parameters_increment_norm Value of norm of parameters increment norm used to stop training.

Definition at line 667 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_minimum_performance_increase ( const double &  new_minimum_performance_increase  ) 

This method sets a new minimum performance improvement during training.

Parameters:
new_minimum_performance_increase Minimum improvement in the performance between two epochs.

Definition at line 697 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_performance_goal ( const double &  new_performance_goal  ) 

This method sets a new goal value for the performance. This is used as a stopping criterium when training a multilayer perceptron

Parameters:
new_performance_goal Goal value for the performance.

Definition at line 728 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_gradient_norm_goal ( const double &  new_gradient_norm_goal  ) 

This method sets a new the goal value for the norm of the objective function gradient. This is used as a stopping criterium when training a multilayer perceptron

Parameters:
new_gradient_norm_goal Goal value for the norm of the objective function gradient.

Definition at line 740 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_maximum_generalization_evaluation_decreases ( const unsigned int &  new_maximum_generalization_evaluation_decreases  ) 

This method sets a new maximum number of generalization failures.

Parameters:
new_maximum_generalization_evaluation_decreases Maximum number of epochs in which the generalization evalutation decreases.

Definition at line 770 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_maximum_epochs_number ( const unsigned int &  new_maximum_epochs_number  ) 

This method sets a maximum number of epochs for training.

Parameters:
new_maximum_epochs_number Maximum number of epochs for training.

Definition at line 800 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_maximum_time ( const double &  new_maximum_time  ) 

This method sets a new maximum training time.

Parameters:
new_maximum_time Maximum training time.

Definition at line 830 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_parameters_history ( const bool &  new_reserve_parameters_history  ) 

This method makes the parameters history vector of vectors to be reseved or not in memory.

Parameters:
new_reserve_parameters_history True if the parameters history vector of vectors is to be reserved, false otherwise.

Definition at line 860 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_parameters_norm_history ( const bool &  new_reserve_parameters_norm_history  ) 

This method makes the parameters norm history vector to be reseved or not in memory.

Parameters:
new_reserve_parameters_norm_history True if the parameters norm history vector is to be reserved, false otherwise.

Definition at line 871 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_evaluation_history ( const bool &  new_reserve_evaluation_history  ) 

This method makes the evaluation history vector to be reseved or not in memory.

Parameters:
new_reserve_evaluation_history True if the evaluation history vector is to be reserved, false otherwise.

Definition at line 882 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_gradient_history ( const bool &  new_reserve_gradient_history  ) 

This method makes the gradient history vector of vectors to be reseved or not in memory.

Parameters:
new_reserve_gradient_history True if the gradient history matrix is to be reserved, false otherwise.

Definition at line 893 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_gradient_norm_history ( const bool &  new_reserve_gradient_norm_history  ) 

This method makes the gradient norm history vector to be reseved or not in memory.

Parameters:
new_reserve_gradient_norm_history True if the gradient norm history matrix is to be reserved, false otherwise.

Definition at line 905 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_inverse_Hessian_history ( const bool &  new_reserve_inverse_Hessian_history  ) 

This method sets the history of the inverse of the Hessian matrix to be reserved or not in memory. This is a vector of matrices.

Parameters:
new_reserve_inverse_Hessian_history True if the inverse Hessian history is to be reserved, false otherwise.

Definition at line 917 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_generalization_evaluation_history ( const bool &  new_reserve_generalization_evaluation_history  ) 

This method makes the Generalization evaluation history to be reserved or not in memory. This is a vector.

Parameters:
new_reserve_generalization_evaluation_history True if the Generalization evaluation history is to be reserved, false otherwise.

Definition at line 941 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_elapsed_time_history ( const bool &  new_reserve_elapsed_time_history  ) 

This method makes the elapsed time over the epochs to be reseved or not in memory. This is a vector.

Parameters:
new_reserve_elapsed_time_history True if the elapsed time history vector is to be reserved, false otherwise.

Definition at line 929 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_reserve_all_training_history ( const bool &   )  [virtual]

This method makes the training history of all variables to be reseved or not in memory.

Definition at line 1662 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::set_display_period ( const unsigned int &  new_display_period  ) 

This method sets a new number of epochs between the training showing progress.

Parameters:
new_display_period Number of epochs between the training showing progress.

Definition at line 953 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::check ( void   )  const [virtual]

This method checks that the Levenberg-Marquard object is ok for training. In particular, it checks that:

  • The performance functional pointer associated to the training algorithm is not NULL,
  • The neural network associated to that performance functional is neither NULL.
  • The data set associated to that performance functional is neither NULL.
If that checkings are not hold, an exception is thrown.

Reimplemented from OpenNN::TrainingAlgorithm.

Definition at line 987 of file levenberg_marquardt_algorithm.cpp.

Vector< double > OpenNN::LevenbergMarquardtAlgorithm::calculate_gradient ( const Vector< double > &  evaluation_terms,
const Matrix< double > &  Jacobian_terms 
) const

This method returns the exact gradient vector of the objective function as a function of the objective terms vector and the objective terms Jacobian matrix.

Parameters:
evaluation_terms Vector with the objective terms values.
Jacobian_terms Jacobian matrix of the objective terms function.

Definition at line 1118 of file levenberg_marquardt_algorithm.cpp.

Matrix< double > OpenNN::LevenbergMarquardtAlgorithm::calculate_Hessian_approximation ( const Matrix< double > &  Jacobian_terms  )  const

This method returns an approximation of the Hessian matrix of the objective function as a function of the objective terms Jacobian.

Parameters:
Jacobian_terms Jacobian matrix of the objective terms function.

Definition at line 1039 of file levenberg_marquardt_algorithm.cpp.

LevenbergMarquardtAlgorithm::LevenbergMarquardtAlgorithmResults * OpenNN::LevenbergMarquardtAlgorithm::perform_training ( void   )  [virtual]

This method trains a neural network with an associated performance functional according to the Levenberg-Marquardt algorithm. Training occurs according to the training parameters.

Implements OpenNN::TrainingAlgorithm.

Definition at line 1301 of file levenberg_marquardt_algorithm.cpp.

std::string OpenNN::LevenbergMarquardtAlgorithm::write_training_algorithm_type ( void   )  const [virtual]

This method writes a string with the type of training algoritm.

Reimplemented from OpenNN::TrainingAlgorithm.

Definition at line 1681 of file levenberg_marquardt_algorithm.cpp.

TiXmlElement * OpenNN::LevenbergMarquardtAlgorithm::to_XML ( void   )  const [virtual]

This method returns a default string representation in XML-type format of the training algorithm object. This containts the training operators, the training parameters, stopping criteria and other stuff.

Reimplemented from OpenNN::TrainingAlgorithm.

Definition at line 1689 of file levenberg_marquardt_algorithm.cpp.

void OpenNN::LevenbergMarquardtAlgorithm::from_XML ( TiXmlElement *  Levenberg_Marquardt_algorithm_element  )  [virtual]

This method loads a Levenberg-Marquardt method object from a XML element. Please mind about the format, wich is specified in the OpenNN manual.

Reimplemented from OpenNN::TrainingAlgorithm.

Definition at line 1939 of file levenberg_marquardt_algorithm.cpp.


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

Generated on Sun Aug 26 11:58:20 2012 for OpenNN by  doxygen 1.5.9