neural_network Class Reference

#include <neural_network.h>

Public Member Functions
	neural_network ()
	neural_network (const std::vector< layer * > &ls)
	~neural_network ()
int	get_num_layers ()
void	print_network_info ()
void	print_network_detailed_info ()
Eigen::VectorXd	predict (const Eigen::VectorXd &input)
Eigen::VectorXd	predict_to_layer (int tolayer, const Eigen::VectorXd &input)
std::vector< Eigen::VectorXd >	predict (const std::vector< Eigen::VectorXd > &input)
std::vector< Eigen::VectorXd >	predict_to_layer (int tolayer, const std::vector< Eigen::VectorXd > &input)
void	network_read (const std::string &filename)
void	network_save (const std::string &filename)
void	add_layer_all_parameters (int wrows, int wcols, int in_dim, int out_dim, std::string type)
void	add_fc_input_layer (int in_dim, int out_dim, std::string type)
void	add_fc_hidden_layer (int out_dim, std::string type)
void	set_layer_weights (int num_layer, Eigen::MatrixXd &weights_)
void	set_layer_biases (int num_layer, Eigen::VectorXd &biases_)
Eigen::MatrixXd	get_layer_weights (int num_layer)
Eigen::VectorXd	get_layer_biases (int num_layer)
double	loss_mse (const std::vector< Eigen::VectorXd > &data, const std::vector< Eigen::VectorXd > &features)
double	accuracy (const std::vector< Eigen::VectorXd > &data, const std::vector< Eigen::VectorXd > &features)
void	SiMEC_1D (std::string output_file, int steps, double delta, bool invert_build, Eigen::VectorXd ipoint)
void	SiMEC_1D_norm_proj (std::string output_file, int steps, double delta, bool invert_build, Eigen::VectorXd ipoint, Eigen::VectorXd &H_inf, Eigen::VectorXd &H_sup)
void	SiMEC_1D_stop_boundary (std::string output_file, int steps, double delta, bool invert_build, Eigen::VectorXd ipoint, Eigen::VectorXd &H_inf, Eigen::VectorXd &H_sup)
void	SiMExp_1D (std::string output_file, double delta, double epsilon, int max_steps, bool invert_build, Eigen::VectorXd &ipoint)
void	ClassChange_1D (std::string output_file, int steps, double delta, bool invert_build, Eigen::VectorXd ipoint)
layer *	get_layer (int n)

Detailed Description

Neural network class.

Constructor & Destructor Documentation

neural_network() [1/2]

neural_network::neural_network ( )

inline

Default constructor.

neural_network() [2/2]

neural_network::neural_network

(

const std::vector< layer * > &

ls

)

Builds a neural network given a vectors of pointers to layers.

~neural_network()

neural_network::~neural_network ( )

inline

Default deconstructor

Member Function Documentation

add_fc_hidden_layer()

void neural_network::add_fc_hidden_layer	(	int	out_dim,
		std::string	type
	)

Adds an hidden layer of a fully-connected feedforward layer to the neural network. Arguments:

• in_dim: dimension of the input space of the layer.
• out_dim: dimension of the output space of the layer.
• type: type of layer.

Note: The last hidden layer built invoking this method is the final layer of the network.

add_fc_input_layer()

void neural_network::add_fc_input_layer	(	int	in_dim,
		int	out_dim,
		std::string	type
	)

Builds the input layer of a fully-connected feedforward layer to the neural network. Arguments:

• in_dim: dimension of the input space of the layer.
• out_dim: dimension of the output space of the layer.
• type: type of layer.

add_layer_all_parameters()

void neural_network::add_layer_all_parameters	(	int	wrows,
		int	wcols,
		int	in_dim,
		int	out_dim,
		std::string	type
	)

Append a layer to the neural network. Arguments:

• wrows: Number of rows of the weights matrix.
• wcols: Number of columns of the weights matrix.
• in_dim: dimension of the input space of the layer.
• out_dim: dimension of the output space of the layer.
• type: type of layer.

Note: For feedforward layers wrows = in_dim and wcols = out_dim.

ClassChange_1D()

void neural_network::ClassChange_1D	(	std::string	output_file,
		int	steps,
		double	delta,
		bool	invert_build,
		Eigen::VectorXd	ipoint
	)

Starting from a point, proceed along the curve which change the output of the network the most. Instead of this method, use SiMExp_1D, which avoids infinite loop by coinstruction.

get_layer_biases()

Eigen::VectorXd neural_network::get_layer_biases

(

int

num_layer

)

Returns a copy of the biases vector of a given layer.

get_layer_weights()

Eigen::MatrixXd neural_network::get_layer_weights

(

int

num_layer

)

Returns a copy of the weights matrix of a given layer.

get_num_layers()

int neural_network::get_num_layers

(

)

Returns the number of layers of the neural network.

network_read()

void neural_network::network_read

(

const std::string &

filename

)

Reads network from file

network_save()

void neural_network::network_save

(

const std::string &

filename

)

Saves network to file

predict() [1/2]

Eigen::VectorXd neural_network::predict

(

const Eigen::VectorXd &

input

)

Computes the output of the neural network for a given input.

predict() [2/2]

std::vector< Eigen::VectorXd > neural_network::predict

(

const std::vector< Eigen::VectorXd > &

input

)

Computes the outputs of the neural network for a given vector of inputs.

predict_to_layer() [1/2]

Eigen::VectorXd neural_network::predict_to_layer	(	int	tolayer,
		const Eigen::VectorXd &	input
	)

Computes the output of the subnetwork up to a specified layer for a given input.

predict_to_layer() [2/2]

std::vector< Eigen::VectorXd > neural_network::predict_to_layer	(	int	tolayer,
		const std::vector< Eigen::VectorXd > &	input
	)

Computes the outputs of the subnetwork up to a specified layer for a given vector of inputs.

print_network_detailed_info()

void neural_network::print_network_detailed_info

(

)

Prints detailed info about the neural network.

print_network_info()

void neural_network::print_network_info

(

)

Prints info about the neural network.

set_layer_biases()

void neural_network::set_layer_biases	(	int	num_layer,
		Eigen::VectorXd &	biases_
	)

Sets the biases of a given layer given a vector in input.

set_layer_weights()

void neural_network::set_layer_weights	(	int	num_layer,
		Eigen::MatrixXd &	weights_
	)

Sets the weights of a given layer given a matrix in input.

SiMEC_1D()

void neural_network::SiMEC_1D	(	std::string	output_file,
		int	steps,
		double	delta,
		bool	invert_build,
		Eigen::VectorXd	ipoint
	)

Basic version of the SiMEC_1D algorithm, bulding the equaivalence class of a point.
Arguments:

• output_file: Name of the file in which the outputs of the algorithm are saved.
• steps: Number of interations of the algorithm.
• delta: Integration step of the algorithm.
• invert_build: Allows to follow a null curve in both directions.
• ipoint: The starting point for which SiMEC_1D builds the equivalence class.

SiMEC_1D_norm_proj()

void neural_network::SiMEC_1D_norm_proj	(	std::string	output_file,
		int	steps,
		double	delta,
		bool	invert_build,
		Eigen::VectorXd	ipoint,
		Eigen::VectorXd &	H_inf,
		Eigen::VectorXd &	H_sup
	)

A modification of the SiMEC_1D algorithm. When it hits the boundary it projects inside the hypercube \((a_1\cdots,a_n) \times (b_1,\cdots,b_n) \).
Arguments:

• output_file: Name of the file in which the outputs of the algorithm are saved.
• steps: Number of interations of the algorithm.
• delta: Integration step of the algorithm.
• invert_build: Allows to follow a null curve in both directions.
• ipoint: The starting point for which SiMEC_1D builds the equivalence class.
• H_inf: The vector \((a_1\cdots,a_n)\).
• H_max: The vector \((b_1,\cdots,b_n) \)

SiMEC_1D_stop_boundary()

void neural_network::SiMEC_1D_stop_boundary	(	std::string	output_file,
		int	steps,
		double	delta,
		bool	invert_build,
		Eigen::VectorXd	ipoint,
		Eigen::VectorXd &	H_inf,
		Eigen::VectorXd &	H_sup
	)

A modification of the SiMEC_1D algorithm. Hitting the boundary of the hypercube \((a_1\cdots,a_n) \times (b_1,\cdots,b_n) \) halts the algorithm.
Arguments:

• output_file: Name of the file in which the outputs of the algorithm are saved.
• steps: Number of interations of the algorithm.
• delta: Integration step of the algorithm.
• invert_build: Allows to follow a null curve in both directions.
• ipoint: The starting point for which SiMEC_1D builds the equivalence class.
• H_inf: The vector \((a_1\cdots,a_n)\).
• H_max: The vector \((b_1,\cdots,b_n) \)

SiMExp_1D()

void neural_network::SiMExp_1D	(	std::string	output_file,
		double	delta,
		double	epsilon,
		int	max_steps,
		bool	invert_build,
		Eigen::VectorXd &	ipoint
	)

SiMExp_1D algorithm. Produces a non-null curve of maximum lenght epsilon starting from a given point.
Arguments:

• output_file: Name of the file in which the outputs of the algorithm are saved.
• steps: Number of interations of the algorithm.
• delta: Integration step of the algorithm.
• epsilon: Maximum distance from the starting point.
• invert_build: Allows to follow a null curve in both directions.
• max_step: The maximum number of iteration; To avoid infinite loops.
• ipoint: The starting point for which SiMEC_1D builds the equivalence class.

---

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

• neural_network.h
• neural_network.cpp