OpenNN::PerceptronLayer Class Reference

#include <perceptron_layer.h>

List of all members.

Public Member Functions

 PerceptronLayer (void)
 PerceptronLayer (const unsigned int &, const unsigned int &)
 PerceptronLayer (const PerceptronLayer &)
virtual ~PerceptronLayer (void)
PerceptronLayeroperator= (const PerceptronLayer &)
bool operator== (const PerceptronLayer &) const
bool is_empty (void) const
const Vector< Perceptron > & get_perceptrons (void) const
const Perceptronget_perceptron (const unsigned int &) const
unsigned int count_inputs_number (void) const
unsigned int count_perceptrons_number (void) const
Vector< double > arrange_biases (void) const
Matrix< double > arrange_synaptic_weights (void) const
unsigned int count_parameters_number (void) const
Vector< double > arrange_parameters (void) const
Vector< unsigned int > count_cumulative_parameters_number (void) const
const
Perceptron::ActivationFunction
get_activation_function (void) const
std::string write_activation_function_name (void) const
const bool & get_display (void) const
void set (void)
void set (const Vector< Perceptron > &)
void set (const unsigned int &, const unsigned int &)
void set (const PerceptronLayer &)
void set_default (void)
void set_inputs_number (const unsigned int &)
void set_perceptrons_number (const unsigned int &)
void set_perceptrons (const Vector< Perceptron > &)
void set_perceptron (const unsigned int &, const Perceptron &)
void set_biases (const Vector< double > &)
void set_synaptic_weights (const Matrix< double > &)
void set_parameters (const Vector< double > &)
void set_activation_function (const Perceptron::ActivationFunction &)
void set_activation_function (const std::string &)
void set_display (const bool &)
void grow_input (void)
void grow_perceptron (void)
void prune_input (const unsigned int &)
void prune_perceptron (const unsigned int &)
void initialize_random (void)
void initialize_biases (const double &)
void initialize_synaptic_weights (const double &)
void initialize_parameters (const double &)
void initialize_parameters_uniform (void)
void initialize_parameters_uniform (const double &, const double &)
void initialize_parameters_uniform (const Vector< double > &, const Vector< double > &)
void initialize_parameters_uniform (const Vector< Vector< double > > &)
void initialize_parameters_normal (void)
void initialize_parameters_normal (const double &, const double &)
void initialize_parameters_normal (const Vector< double > &, const Vector< double > &)
void initialize_parameters_normal (const Vector< Vector< double > > &)
double calculate_parameters_norm (void) const
Vector< double > calculate_combination (const Vector< double > &) const
Matrix< double > calculate_combination_Jacobian (const Vector< double > &) const
Vector< Matrix< double > > calculate_combination_Hessian_form (const Vector< double > &) const
Vector< double > calculate_combination_parameters (const Vector< double > &, const Vector< double > &) const
Matrix< double > calculate_combination_parameters_Jacobian (const Vector< double > &, const Vector< double > &) const
Vector< Matrix< double > > calculate_combination_parameters_Hessian_form (const Vector< double > &, const Vector< double > &) const
Vector< double > calculate_activation (const Vector< double > &) const
Vector< double > calculate_activation_derivative (const Vector< double > &) const
Vector< double > calculate_activation_second_derivative (const Vector< double > &) const
Matrix< double > arrange_activation_Jacobian (const Vector< double > &) const
Vector< Matrix< double > > arrange_activation_Hessian_form (const Vector< double > &) const
Vector< double > calculate_outputs (const Vector< double > &) const
Matrix< double > calculate_Jacobian (const Vector< double > &) const
Vector< Matrix< double > > calculate_Hessian_form (const Vector< double > &) const
Vector< double > calculate_parameters_output (const Vector< double > &, const Vector< double > &) const
Matrix< double > calculate_parameters_Jacobian (const Vector< double > &, const Vector< double > &) const
Vector< Matrix< double > > calculate_parameters_Hessian_form (const Vector< double > &, const Vector< double > &) const
std::string write_expression (const Vector< std::string > &, const Vector< std::string > &) const

Protected Attributes

Vector< Perceptronperceptrons
bool display


Detailed Description

This class represents a layer of perceptrons. Layers of perceptrons will be used to construct multilayer perceptrons.

Definition at line 36 of file perceptron_layer.h.


Constructor & Destructor Documentation

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

Default constructor. It creates a empty layer object, with no perceptrons. This constructor also initializes the rest of class members to their default values.

Definition at line 38 of file perceptron_layer.cpp.

OpenNN::PerceptronLayer::PerceptronLayer ( const unsigned int &  new_inputs_number,
const unsigned int &  new_perceptrons_number 
) [explicit]

Layer architecture constructor. It creates a layer object with given numbers of inputs and perceptrons. The parameters are initialized at random. This constructor also initializes the rest of class members to their default values.

Parameters:
new_inputs_number Number of inputs in the layer.
new_perceptrons_number Number of perceptrons in the layer.

Definition at line 53 of file perceptron_layer.cpp.

OpenNN::PerceptronLayer::PerceptronLayer ( const PerceptronLayer other_perceptron_layer  ) 

Copy constructor. It creates a copy of an existing perceptron layer object.

Parameters:
other_perceptron_layer Perceptron layer object to be copied.

Definition at line 65 of file perceptron_layer.cpp.

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

Destructor. This destructor does not delete any pointer.

Definition at line 76 of file perceptron_layer.cpp.


Member Function Documentation

PerceptronLayer & OpenNN::PerceptronLayer::operator= ( const PerceptronLayer other_perceptron_layer  ) 

Assignment operator. It assigns to this object the members of an existing perceptron layer object.

Parameters:
other_perceptron_layer Perceptron layer object to be assigned.

Definition at line 87 of file perceptron_layer.cpp.

bool OpenNN::PerceptronLayer::operator== ( const PerceptronLayer other_perceptron_layer  )  const

Equal to operator. It compares this object with another object of the same class. It returns true if the members of the two objects have the same values, and false otherwise. @ param other_perceptron_layer Perceptron layer to be compared with.

Definition at line 109 of file perceptron_layer.cpp.

bool OpenNN::PerceptronLayer::is_empty ( void   )  const

This method returns true if the size of the layer is zero, and false otherwise.

Definition at line 130 of file perceptron_layer.cpp.

const Vector< Perceptron > & OpenNN::PerceptronLayer::get_perceptrons ( void   )  const

This method returns a constant reference to the vector of perceptrons defining the layer.

Definition at line 147 of file perceptron_layer.cpp.

const Perceptron & OpenNN::PerceptronLayer::get_perceptron ( const unsigned int &  index  )  const

This method returns a reference to a given element in the perceptrons vector.

Parameters:
index Index of perceptron element.

Definition at line 187 of file perceptron_layer.cpp.

unsigned int OpenNN::PerceptronLayer::count_inputs_number ( void   )  const

This method returns the number of inputs to the layer.

Definition at line 157 of file perceptron_layer.cpp.

unsigned int OpenNN::PerceptronLayer::count_perceptrons_number ( void   )  const

This method returns a reference to the size of the perceptrons vector.

Definition at line 174 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::arrange_biases ( void   )  const

This method returns the biases from all the perceptrons in the layer. The format is a vector of real values. The size of this vector is the number of neurons in the layer.

Definition at line 262 of file perceptron_layer.cpp.

Matrix< double > OpenNN::PerceptronLayer::arrange_synaptic_weights ( void   )  const

This method returns the synaptic weights from the perceptrons. The format is a matrix of real values. The number of rows is the number of neurons in the layer. The number of columns is the number of inputs to the layer.

Definition at line 284 of file perceptron_layer.cpp.

unsigned int OpenNN::PerceptronLayer::count_parameters_number ( void   )  const

This method returns the number of parameters (biases and synaptic weights) of the layer.

Definition at line 216 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::arrange_parameters ( void   )  const

This method returns a single vector with all the layer parameters. The format is a vector of real values. The size is the number of parameters in the layer.

Definition at line 310 of file perceptron_layer.cpp.

Vector< unsigned int > OpenNN::PerceptronLayer::count_cumulative_parameters_number ( void   )  const

This method returns a vector of size the number of neurons in the layer, where each element is equal to the total number of parameters in the current and all the previous neurons.

Definition at line 236 of file perceptron_layer.cpp.

const Perceptron::ActivationFunction & OpenNN::PerceptronLayer::get_activation_function ( void   )  const

This method returns the activation function of the layer. The activation function of a layer is the activation function of all perceptrons in it.

Definition at line 349 of file perceptron_layer.cpp.

std::string OpenNN::PerceptronLayer::write_activation_function_name ( void   )  const

This method returns a string with the name of the layer activation function. This can be: Logistic, HyperbolicTangent, Threshold, SymmetricThreshold or Linear.

Definition at line 375 of file perceptron_layer.cpp.

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

This method returns true if messages from this class are to be displayed on the screen, or false if messages from this class are not to be displayed on the screen.

Definition at line 431 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set ( void   ) 

This method sets an empty layer, wihtout any perceptron. It also sets the rest of members to their default values.

Definition at line 442 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set ( const Vector< Perceptron > &  new_perceptrons  ) 

This method sets a new layer from a given vector of perceptrons. The rest of members of this class are given their defaul values.

Definition at line 455 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set ( const unsigned int &  new_inputs_number,
const unsigned int &  new_perceptrons_number 
)

This method sets new numbers of inputs and perceptrons in the layer. It also sets the rest of members to their default values.

Parameters:
new_inputs_number Number of inputs.
new_perceptrons_number Number of perceptron neurons.

Definition at line 470 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set ( const PerceptronLayer other_perceptron_layer  ) 

This method sets the members of this perceptron layer object with those from other perceptron layer object.

Parameters:
other_perceptron_layer PerceptronLayer object to be copied.

Definition at line 488 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_default ( void   ) 

This method sets those members not related to the vector of perceptrons to their default value.

  • Display: True.

Definition at line 526 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_inputs_number ( const unsigned int &  new_inputs_number  ) 

This method sets a new number of inputs in the layer. The new synaptic weights are initialized at random.

Parameters:
new_inputs_number Number of layer inputs.

Definition at line 538 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_perceptrons_number ( const unsigned int &  new_perceptrons_number  ) 

This method sets a new number perceptrons in the layer. All the parameters are also initialized at random.

Parameters:
new_perceptrons_number New number of neurons in the layer.

Definition at line 555 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_perceptrons ( const Vector< Perceptron > &  new_perceptrons  ) 

This method sets a new vector of percpetrons in the layer.

Parameters:
new_perceptrons Perceptrons vector.

Definition at line 501 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_perceptron ( const unsigned int &  i,
const Perceptron new_perceptron 
)

This method sets a single perceptron in the layer.

Parameters:
i Index of perceptron.
new_perceptron Perceptron neuron to be set.

Definition at line 513 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_biases ( const Vector< double > &  new_biases  ) 

This method sets the biases of all perceptrons in the layer from a single vector.

Parameters:
new_biases New set of biases in the layer.

Definition at line 580 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_synaptic_weights ( const Matrix< double > &  new_synaptic_weights  ) 

This method sets the synaptic weights of this perceptron layer from a single matrix. The format is a matrix of real numbers. The number of rows is the number of neurons in the corresponding layer. The number of columns is the number of inputs to the corresponding layer.

Parameters:
new_synaptic_weights New set of synaptic weights in that layer.

Definition at line 620 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_parameters ( const Vector< double > &  new_parameters  ) 

This method sets the parameters of this layer.

Parameters:
new_parameters Parameters vector for that layer.

Definition at line 670 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_activation_function ( const Perceptron::ActivationFunction new_activation_function  ) 

This class sets a new activation (or transfer) function in a single layer.

Parameters:
new_activation_function Activation function for the layer with the previous index.

Definition at line 718 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_activation_function ( const std::string &  new_activation_function  ) 

This method sets a new activation (or transfer) function in a single layer. The second argument is a string containing the name of the function ("Logistic", "HyperbolicTangent", "Threshold", etc).

Parameters:
new_activation_function Activation function for that layer.

Definition at line 735 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::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 753 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::grow_input ( void   ) 

This method makes the perceptron layer to have one more input.

Definition at line 763 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::grow_perceptron ( void   ) 

This method makes the perceptron layer to have one more perceptron.

Definition at line 778 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::prune_input ( const unsigned int &  index  ) 

This method removes a given input from the layer of perceptrons.

Parameters:
index Index of input to be pruned.

Definition at line 795 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::prune_perceptron ( const unsigned int &  index  ) 

This method removes a given perceptron from the layer.

Parameters:
index Index of perceptron to be pruned.

Definition at line 811 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_random ( void   ) 

This method initializes the perceptron layer with a random number of inputs and a randon number of perceptrons. That can be useful for testing purposes.

Definition at line 822 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_biases ( const double &  value  ) 

This method initializes the biases of all the perceptrons in the layer of perceptrons with a given value.

Parameters:
value Biases initialization value.

Definition at line 838 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_synaptic_weights ( const double &  value  ) 

This method initializes the synaptic weights of all the perceptrons in the layer of perceptrons perceptron with a given value.

Parameters:
value Synaptic weights initialization value.

Definition at line 854 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters ( const double &  value  ) 

This method initializes all the biases and synaptic weights in the neural newtork with a given value.

Parameters:
value Parameters initialization value.

Definition at line 870 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_uniform ( void   ) 

This method initializes all the biases and synaptic weights in the neural newtork at random with values comprised between -1 and +1.

Definition at line 885 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_uniform ( const double &  minimum,
const double &  maximum 
)

This method initializes all the biases and synaptic weights in the layer of perceptrons at random with values comprised between a minimum and a maximum values.

Parameters:
minimum Minimum initialization value.
maximum Maximum initialization value.

Definition at line 904 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_uniform ( const Vector< double > &  minimum,
const Vector< double > &  maximum 
)

This method initializes all the biases and synaptic weights in the layer of perceptrons at random, with values comprised between different minimum and maximum numbers for each parameter.

Parameters:
minimum Vector of minimum initialization values.
maximum Vector of maximum initialization values.

Definition at line 923 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_uniform ( const Vector< Vector< double > > &  minimum_maximum  ) 

This method initializes all the biases and synaptic weights in the layer of perceptrons at random, with values comprised between a different minimum and maximum numbers for each parameter. All minimum are maximum initialization values must be given from a vector of two real vectors. The first element must contain the minimum inizizalization value for each parameter. The second element must contain the maximum inizizalization value for each parameter.

Parameters:
minimum_maximum Vector of minimum and maximum initialization values.

Definition at line 944 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_normal ( void   ) 

This method initializes all the biases and synaptic weights in the newtork with random values chosen from a normal distribution with mean 0 and standard deviation 1.

Definition at line 961 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_normal ( const double &  mean,
const double &  standard_deviation 
)

This method initializes all the biases and synaptic weights in the layer of perceptrons with random random values chosen from a normal distribution with a given mean and a given standard deviation.

Parameters:
mean Mean of normal distribution.
standard_deviation Standard deviation of normal distribution.

Definition at line 980 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_normal ( const Vector< double > &  mean,
const Vector< double > &  standard_deviation 
)

This method initializes all the biases an synaptic weights in the layer of perceptrons with random values chosen from normal distributions with different mean and standard deviation for each parameter.

Parameters:
mean Vector of mean values.
standard_deviation Vector of standard deviation values.

Definition at line 999 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_parameters_normal ( const Vector< Vector< double > > &  mean_standard_deviation  ) 

This method initializes all the biases and synaptic weights in the layer of perceptrons with random values chosen from normal distributions with different mean and standard deviation for each parameter. All mean and standard deviation values are given from a vector of two real vectors. The first element must contain the mean value for each parameter. The second element must contain the standard deviation value for each parameter.

Parameters:
mean_standard_deviation Vector of mean and standard deviation values.

Definition at line 1020 of file perceptron_layer.cpp.

double OpenNN::PerceptronLayer::calculate_parameters_norm ( void   )  const

This method calculates the norm of a layer parameters vector.

Definition at line 1036 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_combination ( const Vector< double > &  inputs  )  const

This method returns the combination to every perceptron in the layer as a function of the inputs to that layer.

Parameters:
inputs Input to the layer with the previous index.

Definition at line 1047 of file perceptron_layer.cpp.

Matrix< double > OpenNN::PerceptronLayer::calculate_combination_Jacobian ( const Vector< double > &   )  const

This method returns the partial derivatives of the combination of a layer with respect to the inputs. All that partial derivatives are arranged in the so called Jacobian matrix of the layer combination function.

Definition at line 1090 of file perceptron_layer.cpp.

Vector< Matrix< double > > OpenNN::PerceptronLayer::calculate_combination_Hessian_form ( const Vector< double > &   )  const

This method returns the second partial derivatives of the combination of a layer with respect to the inputs of that layer. All that partial derivatives are arranged in the so called Hessian form, represented as a vector of matrices, of the layer combination function.

Definition at line 1101 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_combination_parameters ( const Vector< double > &  inputs,
const Vector< double > &  parameters 
) const

This method returns which would be the combination of a layer as a function of the inputs and for a set of parameters.

Parameters:
inputs Vector of inputs to that layer.
parameters Vector of parameters in the layer.

Definition at line 1123 of file perceptron_layer.cpp.

Matrix< double > OpenNN::PerceptronLayer::calculate_combination_parameters_Jacobian ( const Vector< double > &  inputs,
const Vector< double > &   
) const

This method returns the partial derivatives of the combination of a layer with respect to the parameters in that layer, for a given set of inputs. All that partial derivatives are arranged in the so called Jacobian matrix of the layer combination function.

Parameters:
inputs Vector of inputs to that layer.

Definition at line 1174 of file perceptron_layer.cpp.

Vector< Matrix< double > > OpenNN::PerceptronLayer::calculate_combination_parameters_Hessian_form ( const Vector< double > &  ,
const Vector< double > &   
) const

This method returns the second partial derivatives of the combination of a layer with respect to the parameters in that layer, for a given set of inputs. All that partial derivatives are arranged in the so called Hessian form, represented as a vector of matrices, of the layer combination function.

Todo:

Definition at line 1210 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_activation ( const Vector< double > &  combination  )  const

This method returns the outputs from every perceptron in a layer as a function of their combination.

Parameters:
combination Combination to every neuron in the layer with the previous index.

Definition at line 1232 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_activation_derivative ( const Vector< double > &  combination  )  const

This method returns the activation derivative from every perceptron in a layer as a function of their combination.

Parameters:
combination Combination to every neuron in the layer with the previous index.

Definition at line 1273 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_activation_second_derivative ( const Vector< double > &  combination  )  const

This method returns the activation second derivative from every perceptron as a function of their combination.

Parameters:
combination Combination to every perceptron in the layer.

Definition at line 1314 of file perceptron_layer.cpp.

Matrix< double > OpenNN::PerceptronLayer::arrange_activation_Jacobian ( const Vector< double > &  activation_derivative  )  const

This method arranges a "Jacobian" matrix from a vector of derivatives.

Parameters:
activation_derivative Vector of activation function derivatives.

Definition at line 1355 of file perceptron_layer.cpp.

Vector< Matrix< double > > OpenNN::PerceptronLayer::arrange_activation_Hessian_form ( const Vector< double > &  activation_second_derivative  )  const

This method arranges a "Hessian form" vector of matrices from a vector of second derivatives.

Parameters:
activation_second_derivative Vector of activation function second derivatives.

Definition at line 1372 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_outputs ( const Vector< double > &  inputs  )  const

This method returns the outputs from every perceptron in a layer as a function of their inputs.

Parameters:
inputs Input vector to the layer with the previous index.

Definition at line 1393 of file perceptron_layer.cpp.

Matrix< double > OpenNN::PerceptronLayer::calculate_Jacobian ( const Vector< double > &  inputs  )  const

This method returns the Jacobian matrix of a layer for a given inputs to that layer. This is composed by the derivatives of the layer outputs with respect to their inputs. The number of rows is the number of neurons in the layer. The number of columns is the number of inputs to that layer.

Parameters:
inputs Input to layer.

Definition at line 1428 of file perceptron_layer.cpp.

Vector< Matrix< double > > OpenNN::PerceptronLayer::calculate_Hessian_form ( const Vector< double > &  inputs  )  const

This method returns the second partial derivatives of the outputs from a layer with respect to the inputs to that layer.

Parameters:
inputs Vector of inputs to that layer.

Definition at line 1469 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_parameters_output ( const Vector< double > &  inputs,
const Vector< double > &  parameters 
) const

This method returns which would be the outputs from a layer for a given inputs to that layer and a set of parameters in that layer.

Parameters:
inputs Vector of inputs to that layer.
parameters Vector of parameters in that layer.

Definition at line 1501 of file perceptron_layer.cpp.

Matrix< double > OpenNN::PerceptronLayer::calculate_parameters_Jacobian ( const Vector< double > &  inputs,
const Vector< double > &  parameters 
) const

This method returns the parameters Jacobian for a given set of inputs. This is composed by the derivatives of the layer outputs with respect to the layer parameters. The number of rows is the number of neurons in the layer. The number of columns is the number of parameters in that layer.

Parameters:
inputs Set of inputs to the layer.
parameters Set of layer parameters.

Definition at line 1556 of file perceptron_layer.cpp.

Vector< Matrix< double > > OpenNN::PerceptronLayer::calculate_parameters_Hessian_form ( const Vector< double > &  inputs,
const Vector< double > &  parameters 
) const

This method returns the second partial derivatives of the outputs from a layer with respect to the parameters in that layer, for a given inputs to that layer. This quantity is the Hessian form of the layer outputs function, and it is represented as a vector of matrices.

Parameters:
inputs Set of layer inputs.
parameters Set of layer parameters.

Definition at line 1597 of file perceptron_layer.cpp.

std::string OpenNN::PerceptronLayer::write_expression ( const Vector< std::string > &  inputs_name,
const Vector< std::string > &  outputs_name 
) const

This method returns a string with the expression of the inputs-outputs relationship of the layer.

Parameters:
inputs_name Vector of strings with the name of the layer inputs.
outputs_name Vector of strings with the name of the layer outputs.

Definition at line 1648 of file perceptron_layer.cpp.


Member Data Documentation

Vectors of perceptrons which defines the layer. The size of the vector is equal to the number of perceptrons in the layer.

Definition at line 206 of file perceptron_layer.h.

Display messages to screen.

Definition at line 210 of file perceptron_layer.h.


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

Generated on Sun Aug 26 11:58:18 2012 for OpenNN by  doxygen 1.5.9