OpenNN::LevenbergMarquardtAlgorithm::LevenbergMarquardtAlgorithmResults Struct Reference

#include <levenberg_marquardt_algorithm.h>

Inheritance diagram for OpenNN::LevenbergMarquardtAlgorithm::LevenbergMarquardtAlgorithmResults:

OpenNN::TrainingAlgorithm::Results

List of all members.

Public Member Functions

void resize_training_history (const unsigned int &)
std::string to_string (void) const

Public Attributes

Vector< Vector< double > > parameters_history
Vector< double > parameters_norm_history
Vector< double > evaluation_history
Vector< double > generalization_evaluation_history
Vector< Vector< double > > gradient_history
Vector< double > gradient_norm_history
Vector< Matrix< double > > Hessian_approximation_history
Vector< double > damping_parameter_history
Vector< double > elapsed_time_history
Vector< double > final_parameters
double final_parameters_norm
double final_evaluation
double final_generalization_evaluation
Vector< double > final_gradient
double final_gradient_norm
double elapsed_time


Detailed Description

This structure contains the training results for the Levenberg-Marquardt algorithm.

Definition at line 66 of file levenberg_marquardt_algorithm.h.


Member Function Documentation

void OpenNN::LevenbergMarquardtAlgorithm::LevenbergMarquardtAlgorithmResults::resize_training_history ( const unsigned int &  new_size  ) 

This method resizes all the training history variables.

Parameters:
new_size Size of training history variables.

Definition at line 1187 of file levenberg_marquardt_algorithm.cpp.

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

This method returns a string representation of the current Levenberg-Marquardt algorithm results structure.

Reimplemented from OpenNN::TrainingAlgorithm::Results.

Definition at line 1207 of file levenberg_marquardt_algorithm.cpp.


Member Data Documentation

History of the neural network parameters over the training epochs.

Definition at line 72 of file levenberg_marquardt_algorithm.h.

History of the parameters norm over the training epochs.

Definition at line 76 of file levenberg_marquardt_algorithm.h.

History of the performance function evaluation over the training epochs.

Definition at line 80 of file levenberg_marquardt_algorithm.h.

History of the generalization evaluation over the training epochs.

Definition at line 84 of file levenberg_marquardt_algorithm.h.

History of the performance function gradient over the training epochs.

Definition at line 88 of file levenberg_marquardt_algorithm.h.

History of the gradient norm over the training epochs.

Definition at line 92 of file levenberg_marquardt_algorithm.h.

History of the Hessian approximation over the training epochs.

Definition at line 96 of file levenberg_marquardt_algorithm.h.

History of the damping parameter over the training epochs.

Definition at line 100 of file levenberg_marquardt_algorithm.h.

History of the elapsed time over the training epochs.

Definition at line 104 of file levenberg_marquardt_algorithm.h.

Final neural network parameters vector.

Definition at line 110 of file levenberg_marquardt_algorithm.h.

Final neural network parameters norm.

Definition at line 114 of file levenberg_marquardt_algorithm.h.

Final performance function evaluation.

Definition at line 118 of file levenberg_marquardt_algorithm.h.

Final generalization evaluation.

Definition at line 122 of file levenberg_marquardt_algorithm.h.

Final performance function gradient.

Definition at line 126 of file levenberg_marquardt_algorithm.h.

Final gradient norm.

Definition at line 130 of file levenberg_marquardt_algorithm.h.

Elapsed time of the training process.

Definition at line 134 of file levenberg_marquardt_algorithm.h.


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

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