OpenNN  2.2
Open Neural Networks Library
Public Member Functions | Protected Attributes | List of all members
OpenNN::PerceptronLayer Class Reference

#include <perceptron_layer.h>

Public Member Functions

 PerceptronLayer (void)
 
 PerceptronLayer (const size_t &, const size_t &)
 
 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 size_t &) const
 
size_t get_inputs_number (void) const
 
size_t get_perceptrons_number (void) const
 
Vector< double > arrange_biases (void) const
 
Matrix< double > arrange_synaptic_weights (void) const
 
size_t count_parameters_number (void) const
 
Vector< double > arrange_parameters (void) const
 
size_t count_perceptron_parameters_number (void) const
 
Vector< Vector< double > > arrange_perceptrons_parameters (void) const
 
Vector< size_t > count_cumulative_parameters_number (void) const
 
const Perceptron::ActivationFunctionget_activation_function (void) const
 
std::string write_activation_function (void) const
 
const bool & get_display (void) const
 
void set (void)
 
void set (const Vector< Perceptron > &)
 
void set (const size_t &, const size_t &)
 
void set (const PerceptronLayer &)
 
void set_default (void)
 
void set_inputs_number (const size_t &)
 
void set_perceptrons_number (const size_t &)
 
void set_perceptrons (const Vector< Perceptron > &)
 
void set_perceptron (const size_t &, 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_inputs (const size_t &)
 
void grow_perceptrons (const size_t &)
 
void prune_input (const size_t &)
 
void prune_perceptron (const size_t &)
 
void initialize_random (void)
 
void initialize_biases (const double &)
 
void initialize_synaptic_weights (const double &)
 
void initialize_parameters (const double &)
 
void randomize_parameters_uniform (void)
 
void randomize_parameters_uniform (const double &, const double &)
 
void randomize_parameters_uniform (const Vector< double > &, const Vector< double > &)
 
void randomize_parameters_uniform (const Vector< Vector< double > > &)
 
void randomize_parameters_normal (void)
 
void randomize_parameters_normal (const double &, const double &)
 
void randomize_parameters_normal (const Vector< double > &, const Vector< double > &)
 
void randomize_parameters_normal (const Vector< Vector< double > > &)
 
double calculate_parameters_norm (void) const
 
Vector< double > calculate_combinations (const Vector< double > &) const
 
Matrix< double > calculate_combinations_Jacobian (const Vector< double > &) const
 
Vector< Matrix< double > > calculate_combinations_Hessian_form (const Vector< double > &) const
 
Vector< double > calculate_combinations (const Vector< double > &, const Vector< double > &) const
 
Matrix< double > calculate_combinations_Jacobian (const Vector< double > &, const Vector< double > &) const
 
Vector< Matrix< double > > calculate_combinations_Hessian_form (const Vector< double > &, const Vector< double > &) const
 
Vector< double > calculate_activations (const Vector< double > &) const
 
Vector< double > calculate_activations_derivatives (const Vector< double > &) const
 
Vector< double > calculate_activations_second_derivatives (const Vector< double > &) const
 
Matrix< double > arrange_activations_Jacobian (const Vector< double > &) const
 
Vector< Matrix< double > > arrange_activations_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_outputs (const Vector< double > &, const Vector< double > &) const
 
Matrix< double > calculate_Jacobian (const Vector< double > &, const Vector< double > &) const
 
Vector< Matrix< double > > calculate_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 39 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 27 of file perceptron_layer.cpp.

OpenNN::PerceptronLayer::PerceptronLayer ( const size_t &  new_inputs_number,
const size_t &  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_numberNumber of inputs in the layer.
new_perceptrons_numberNumber of perceptrons in the layer.

Definition at line 42 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_layerPerceptron layer object to be copied.

Definition at line 54 of file perceptron_layer.cpp.

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

Destructor. This destructor does not delete any pointer.

Definition at line 65 of file perceptron_layer.cpp.

Member Function Documentation

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

Arranges a "Hessian form" vector of matrices from a vector of second derivatives.

Parameters
activation_second_derivativeVector of activation function second derivatives.

Definition at line 1457 of file perceptron_layer.cpp.

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

Arranges a "Jacobian" matrix from a vector of derivatives.

Parameters
activation_derivativeVector of activation function derivatives.

Definition at line 1440 of file perceptron_layer.cpp.

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

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 251 of file perceptron_layer.cpp.

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

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 299 of file perceptron_layer.cpp.

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

Returns the parameters of every single perceptron in the layer. The format is a vector of vectors. The size is equal to the number of perceptrons in the layer. Each element contains the parameters of a perceptron, with size one plus the number of inputs in this layer.

Definition at line 353 of file perceptron_layer.cpp.

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

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 273 of file perceptron_layer.cpp.

Vector< double > OpenNN::PerceptronLayer::calculate_activations ( const Vector< double > &  combinations) const

Returns the activations from every perceptron in a layer as a function of their combination.

Parameters
combinationsCombination from every neuron in the layer.

Definition at line 1317 of file perceptron_layer.cpp.

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

Returns the activation derivative from every perceptron in the layer as a function of its combination.

Parameters
combinationCombination to every neuron in the layer.

Definition at line 1358 of file perceptron_layer.cpp.

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

Returns the activation second derivative from every perceptron as a function of their combination.

Parameters
combinationCombination to every perceptron in the layer.

Definition at line 1399 of file perceptron_layer.cpp.

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

Returns the combination to every perceptron in the layer as a function of the inputs to that layer.

Parameters
inputsInputs to the layer.

Definition at line 1117 of file perceptron_layer.cpp.

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

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

Parameters
inputsVector of inputs to that layer.
parametersVector of parameters in the layer.

Definition at line 1194 of file perceptron_layer.cpp.

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

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 1172 of file perceptron_layer.cpp.

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

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.

Definition at line 1295 of file perceptron_layer.cpp.

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

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 1160 of file perceptron_layer.cpp.

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

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
inputsVector of inputs to that layer.

Definition at line 1258 of file perceptron_layer.cpp.

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

Returns the second partial derivatives of the outputs from a layer with respect to the inputs to that layer.

Parameters
inputsVector of inputs to that layer.

Definition at line 1552 of file perceptron_layer.cpp.

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

Returns the second partial derivatives of the outputs from a layer with respect a given set of potential parameters for this layer, and for a given set of inputs. This quantity is the Hessian form of the layer outputs function, and it is represented as a vector of matrices.

Parameters
inputsSet of layer inputs.
parametersSet of layer parameters.

Definition at line 1677 of file perceptron_layer.cpp.

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

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
inputsInput to layer.

Definition at line 1513 of file perceptron_layer.cpp.

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

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
inputsSet of inputs to the layer.
parametersSet of layer parameters.

Definition at line 1635 of file perceptron_layer.cpp.

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

Returns the outputs from every perceptron in a layer as a function of their inputs.

Parameters
inputsInput vector to the layer.

Definition at line 1478 of file perceptron_layer.cpp.

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

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
inputsVector of inputs to that layer.
parametersVector of parameters in that layer.

Definition at line 1584 of file perceptron_layer.cpp.

Vector< size_t > OpenNN::PerceptronLayer::count_cumulative_parameters_number ( void  ) const

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 225 of file perceptron_layer.cpp.

size_t OpenNN::PerceptronLayer::count_perceptron_parameters_number ( void  ) const

Returns the number of parameters of each perceptron in this layer. This is equal to one plus the number of inputs.

Definition at line 338 of file perceptron_layer.cpp.

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

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 373 of file perceptron_layer.cpp.

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

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 455 of file perceptron_layer.cpp.

const Perceptron & OpenNN::PerceptronLayer::get_perceptron ( const size_t &  index) const

Returns a reference to a given element in the perceptrons vector.

Parameters
indexIndex of perceptron element.

Definition at line 176 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::grow_inputs ( const size_t &  inputs_number)

Makes the perceptron layer to have more inputs.

Parameters
inputs_numberNumber of inputs to be added.

Definition at line 788 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::grow_perceptrons ( const size_t &  perceptrons_number)

Makes the perceptron layer to have more perceptrons.

Parameters
perceptrons_numberNumber of perceptrons to be added.

Definition at line 807 of file perceptron_layer.cpp.

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

Initializes the biases of all the perceptrons in the layer of perceptrons with a given value.

Parameters
valueBiases initialization value.

Definition at line 908 of file perceptron_layer.cpp.

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

Initializes all the biases and synaptic weights in the neural newtork with a given value.

Parameters
valueParameters initialization value.

Definition at line 940 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::initialize_random ( void  )

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 892 of file perceptron_layer.cpp.

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

Initializes the synaptic weights of all the perceptrons in the layer of perceptrons perceptron with a given value.

Parameters
valueSynaptic weights initialization value.

Definition at line 924 of file perceptron_layer.cpp.

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_layerPerceptron layer object to be assigned.

Definition at line 76 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 98 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::prune_input ( const size_t &  index)

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

Parameters
indexIndex of input to be pruned.

Definition at line 827 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::prune_perceptron ( const size_t &  index)

This method removes a given perceptron from the layer.

Parameters
indexIndex of perceptron to be pruned.

Definition at line 862 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::randomize_parameters_normal ( void  )

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 1031 of file perceptron_layer.cpp.

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

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
meanMean of normal distribution.
standard_deviationStandard deviation of normal distribution.

Definition at line 1050 of file perceptron_layer.cpp.

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

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
meanVector of mean values.
standard_deviationVector of standard deviation values.

Definition at line 1069 of file perceptron_layer.cpp.

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

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_deviationVector of mean and standard deviation values.

Definition at line 1090 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::randomize_parameters_uniform ( void  )

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

Definition at line 955 of file perceptron_layer.cpp.

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

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
minimumMinimum initialization value.
maximumMaximum initialization value.

Definition at line 974 of file perceptron_layer.cpp.

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

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
minimumVector of minimum initialization values.
maximumVector of maximum initialization values.

Definition at line 993 of file perceptron_layer.cpp.

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

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_maximumVector of minimum and maximum initialization values.

Definition at line 1014 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set ( void  )

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

Definition at line 466 of file perceptron_layer.cpp.

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

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 479 of file perceptron_layer.cpp.

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

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

Parameters
new_inputs_numberNumber of inputs.
new_perceptrons_numberNumber of perceptron neurons.

Definition at line 494 of file perceptron_layer.cpp.

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

Sets the members of this perceptron layer object with those from other perceptron layer object.

Parameters
other_perceptron_layerPerceptronLayer object to be copied.

Definition at line 512 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_functionActivation function for the layer.

Definition at line 742 of file perceptron_layer.cpp.

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

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_functionActivation function for that layer.

Definition at line 759 of file perceptron_layer.cpp.

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

Sets the biases of all perceptrons in the layer from a single vector.

Parameters
new_biasesNew set of biases in the layer.

Definition at line 604 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_default ( void  )

Sets those members not related to the vector of perceptrons to their default value.

  • Display: True.

Definition at line 550 of file perceptron_layer.cpp.

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

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_displayDisplay value.

Definition at line 777 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_inputs_number ( const size_t &  new_inputs_number)

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

Parameters
new_inputs_numberNumber of layer inputs.

Definition at line 562 of file perceptron_layer.cpp.

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

Sets the parameters of this layer.

Parameters
new_parametersParameters vector for that layer.

Definition at line 694 of file perceptron_layer.cpp.

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

Sets a single perceptron in the layer.

Parameters
iIndex of perceptron.
new_perceptronPerceptron neuron to be set.

Definition at line 537 of file perceptron_layer.cpp.

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

Sets a new vector of percpetrons in the layer.

Parameters
new_perceptronsPerceptrons vector.

Definition at line 525 of file perceptron_layer.cpp.

void OpenNN::PerceptronLayer::set_perceptrons_number ( const size_t &  new_perceptrons_number)

Sets a new number perceptrons in the layer. All the parameters are also initialized at random.

Parameters
new_perceptrons_numberNew number of neurons in the layer.

Definition at line 579 of file perceptron_layer.cpp.

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

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_weightsNew set of synaptic weights in that layer.

Definition at line 644 of file perceptron_layer.cpp.

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

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

Definition at line 399 of file perceptron_layer.cpp.

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

Returns a string with the expression of the inputs-outputs relationship of the layer.

Parameters
inputs_nameVector of strings with the name of the layer inputs.
outputs_nameVector of strings with the name of the layer outputs.

Definition at line 1728 of file perceptron_layer.cpp.

Member Data Documentation

Vector<Perceptron> OpenNN::PerceptronLayer::perceptrons
protected

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 212 of file perceptron_layer.h.


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