#include <root_mean_squared_error.h>
Public Member Functions | |
RootMeanSquaredError (void) | |
RootMeanSquaredError (NeuralNetwork *) | |
RootMeanSquaredError (DataSet *) | |
RootMeanSquaredError (NeuralNetwork *, DataSet *) | |
RootMeanSquaredError (TiXmlElement *) | |
virtual | ~RootMeanSquaredError (void) |
void | check (void) const |
double | calculate_evaluation (void) const |
double | calculate_evaluation (const Vector< double > &) const |
double | calculate_generalization_evaluation (void) const |
Vector< double > | calculate_gradient (void) const |
Matrix< double > | calculate_Hessian (void) const |
std::string | write_performance_term_type (void) const |
TiXmlElement * | to_XML (void) const |
void | from_XML (TiXmlElement *) |
Definition at line 29 of file root_mean_squared_error.h.
OpenNN::RootMeanSquaredError::RootMeanSquaredError | ( | void | ) | [explicit] |
Default constructor. It creates a root mean squared error performance term object not associated to any neural network and not measured on any data set. It also initializes all the rest of class members to their default values.
Definition at line 44 of file root_mean_squared_error.cpp.
OpenNN::RootMeanSquaredError::RootMeanSquaredError | ( | NeuralNetwork * | new_neural_network_pointer | ) | [explicit] |
Neural network constructor. It creates a root mean squared error associated to a neural network object but not to a data set object. It also initializes all the rest of class members to their default values.
new_neural_network_pointer | Pointer to a neural network object. |
Definition at line 56 of file root_mean_squared_error.cpp.
OpenNN::RootMeanSquaredError::RootMeanSquaredError | ( | DataSet * | new_data_set_pointer | ) | [explicit] |
Data set constructor. It creates a root mean squared error associated to a data set object but not to a neural network object. It also initializes all the rest of class members to their default values.
new_data_set_pointer | Pointer to a data set object. |
Definition at line 69 of file root_mean_squared_error.cpp.
OpenNN::RootMeanSquaredError::RootMeanSquaredError | ( | NeuralNetwork * | new_neural_network_pointer, | |
DataSet * | new_data_set_pointer | |||
) | [explicit] |
Neural network and data set constructor. It creates a root mean squared error performance term object associated to a neural network and measured on a data set. It also initializes all the rest of class members to their default values.
new_neural_network_pointer | Pointer to a neural network object. | |
new_data_set_pointer | Pointer to a data set object. |
Definition at line 84 of file root_mean_squared_error.cpp.
OpenNN::RootMeanSquaredError::RootMeanSquaredError | ( | TiXmlElement * | root_mean_squared_error_element | ) | [explicit] |
XML constructor. This constructor creates a root mean squared object neither associated to a neural network nor a data set. It also loads the member data from a XML element.
root_mean_squared_error_element | TinyXML element with the object members. |
Definition at line 97 of file root_mean_squared_error.cpp.
OpenNN::RootMeanSquaredError::~RootMeanSquaredError | ( | void | ) | [virtual] |
void OpenNN::RootMeanSquaredError::check | ( | void | ) | const [virtual] |
This method checks that there are a neural network and a data set associated to the root mean squared error, and that the numbers of inputs and outputs in the neural network are equal to the numbers of inputs and targets in the data set. If some of the above conditions is not hold, the method throws an exception.
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 120 of file root_mean_squared_error.cpp.
double OpenNN::RootMeanSquaredError::calculate_evaluation | ( | void | ) | const [virtual] |
This method returns the evaluation value of a neural network according to the root mean squared error on the training instances of a data set.
Implements OpenNN::PerformanceTerm.
Definition at line 209 of file root_mean_squared_error.cpp.
double OpenNN::RootMeanSquaredError::calculate_evaluation | ( | const Vector< double > & | parameters | ) | const [virtual] |
This method returns which would be the objective of a multilayer perceptron for an hypothetical vector of parameters. It does not set that vector of parameters to the multilayer perceptron.
parameters | Vector of a potential parameters for the multilayer perceptron associated to the performance term. |
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 270 of file root_mean_squared_error.cpp.
double OpenNN::RootMeanSquaredError::calculate_generalization_evaluation | ( | void | ) | const [virtual] |
This method returns the root mean squared error of the multilayer perceptron measured on the generalization instances of the data set.
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 409 of file root_mean_squared_error.cpp.
Vector< double > OpenNN::RootMeanSquaredError::calculate_gradient | ( | void | ) | const [virtual] |
This method calculates the gradient the root mean squared error funcion by means of the back-propagation algorithm.
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 315 of file root_mean_squared_error.cpp.
Matrix< double > OpenNN::RootMeanSquaredError::calculate_Hessian | ( | void | ) | const [virtual] |
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 465 of file root_mean_squared_error.cpp.
std::string OpenNN::RootMeanSquaredError::write_performance_term_type | ( | void | ) | const [virtual] |
This method returns a string with the name of the root mean squared error performance type, "ROOT_MEAN_SQUARED_ERROR".
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 477 of file root_mean_squared_error.cpp.
TiXmlElement * OpenNN::RootMeanSquaredError::to_XML | ( | void | ) | const [virtual] |
This method serializes the root mean squared error object into a XML element of the TinyXML library. See the OpenNN manual for more information about the format of this element.
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 488 of file root_mean_squared_error.cpp.
void OpenNN::RootMeanSquaredError::from_XML | ( | TiXmlElement * | ) | [virtual] |
Reimplemented from OpenNN::PerformanceTerm.
Definition at line 517 of file root_mean_squared_error.cpp.