layer Class Reference

Generic layer class. More...

#include <layer.h>

Public Member Functions
	layer ()
	layer (const std::vector< std::vector< double >> &weights_, const std::vector< double > &biases_)
	layer (const std::vector< std::vector< double >> &weights_)
	layer (const Eigen::MatrixXd &weights_)
	layer (const Eigen::MatrixXd &weights_, const std::vector< double > &biases_)
	layer (const Eigen::MatrixXd &weights_, const Eigen::VectorXd &biases_)
	layer (const Eigen::MatrixXd &weights_, const Eigen::VectorXd &biases_, int in_dim, int out_dim)
virtual	~layer ()
virtual Eigen::VectorXd	predict (const Eigen::VectorXd &input)
virtual std::vector< Eigen::VectorXd >	predict_batch (const std::vector< Eigen::VectorXd > &input)
const Eigen::VectorXd	get_biases ()
const Eigen::MatrixXd	get_weights ()
const Eigen::MatrixXd	get_weights_biases_as_mat ()
const Eigen::MatrixXd	get_weights_biases_as_vec_col_maj ()
const Eigen::MatrixXd	get_weights_biases_as_vec_row_maj ()
double	get_weight (int i, int j)
double	get_bias (int i)
void	set_biases (const Eigen::VectorXd &biases_)
void	set_biases (const std::vector< double > &biases_)
void	set_weights (const Eigen::MatrixXd &weights_)
void	set_weight (int i, int j, double weight_)
void	set_bias (int i, double bias_)
void	set_weights_biases_compact (Eigen::MatrixXd &source)
void	set_weights_biases (Eigen::MatrixXd &source)
void	set_weights_biases_row_maj (Eigen::MatrixXd &source)
int	get_num_nodes ()
int	get_input_size ()
int	get_weights_rows ()
int	get_weights_cols ()
std::string	get_type ()
virtual Eigen::MatrixXd	compute_partial_derivatives_wrt_inputs (Eigen::VectorXd &input)=0
virtual Eigen::MatrixXd	compute_partial_derivatives_wrt_weights_biases (Eigen::VectorXd &input)=0
void	transpose_weights ()
void	set_exp_max_cut (double exp_max_cut_)
void	set_exp_zero_approx (double exp_zero_approx_)
double	get_exp_max_cut ()
double	get_exp_zero_approx ()

Protected Attributes
Eigen::VectorXd	biases
Eigen::MatrixXd	weights
int	weights_rows = 0
int	input_dim = 0
int	output_dim = 0
int	weights_cols = 0
std::string	type
double	exp_max_cut = 50.
double	exp_zero_approx = 1.92874984e-22

Detailed Description

Generic layer class.

The class layer is an abstract class to be used to realize different kind of layers.

Constructor & Destructor Documentation

layer() [1/7]

layer::layer ( )

inline

Default constructor.

layer() [2/7]

layer::layer	(	const std::vector< std::vector< double >> &	weights_,
		const std::vector< double > &	biases_
	)

Initializes a generic layer given a matrix of weights and a vector of biases.

layer() [3/7]

layer::layer

(

const std::vector< std::vector< double >> &

weights_

)

Initializes a generic layer given a matrix of weights and a vector of biases.

layer() [4/7]

layer::layer

(

const Eigen::MatrixXd &

weights_

)

Initializes a generic layer given a matrix of weights and a vector of biases.

layer() [5/7]

layer::layer	(	const Eigen::MatrixXd &	weights_,
		const std::vector< double > &	biases_
	)

Initializes a generic layer given a matrix of weights and a vector of biases.

layer() [6/7]

layer::layer	(	const Eigen::MatrixXd &	weights_,
		const Eigen::VectorXd &	biases_
	)

Initializes a generic layer given a matrix of weights and a vector of biases.

layer() [7/7]

layer::layer	(	const Eigen::MatrixXd &	weights_,
		const Eigen::VectorXd &	biases_,
		int	in_dim,
		int	out_dim
	)

Initializes a generic layer given a matrix of weights and a vector of biases.

~layer()

virtual layer::~layer ( )

inlinevirtual

Default deconstructor.

Member Function Documentation

compute_partial_derivatives_wrt_inputs()

virtual Eigen::MatrixXd layer::compute_partial_derivatives_wrt_inputs ( Eigen::VectorXd &  input )

pure virtual

Computes the Jacobian matrix with respect to the input variables. The Jacobian is computer in reduced form.

Implemented in fc_layer_sg, fc_layer_sl, fc_layer_sm, and fc_layer_sp.

compute_partial_derivatives_wrt_weights_biases()

virtual Eigen::MatrixXd layer::compute_partial_derivatives_wrt_weights_biases ( Eigen::VectorXd &  input )

pure virtual

Computes the Jacobian matrix with respect to weights and biases.

Implemented in fc_layer_sg, fc_layer_sl, fc_layer_sm, and fc_layer_sp.

get_bias()

double layer::get_bias

(

int

i

)

Returns the bias of the i-th node.

get_biases()

const Eigen::VectorXd layer::get_biases

(

)

Returns the biases of the layer.

get_exp_max_cut()

double layer::get_exp_max_cut

(

)

Returns the parameter exp_max_cut, controlling the approximations of \( f(x) = e^{-x} \) and \( f(x) = ln(1+e^{x}) \) for large values of the argument \( x \).

get_exp_zero_approx()

double layer::get_exp_zero_approx

(

)

Returns the parameter exp_zero_approx, approximating \( f(x) = e^{-x} \) for large values of the argument \( x \).

get_input_size()

int layer::get_input_size

(

)

Returns the dimension of the input space of the layer.

get_num_nodes()

int layer::get_num_nodes

(

)

Returns the number of nodes of the layer.

get_type()

std::string layer::get_type

(

)

Returns the type of the layer.

get_weight()

double layer::get_weight	(	int	i,
		int	j
	)

Returns the (i-th,j-th) entry of the matrix of weights.

get_weights()

const Eigen::MatrixXd layer::get_weights

(

)

Returns the weights of the layer.

get_weights_biases_as_mat()

const Eigen::MatrixXd layer::get_weights_biases_as_mat

(

)

Returns the weights and the biases of the layers in a matrix whose last column is the vector of the biases.

get_weights_biases_as_vec_col_maj()

const Eigen::MatrixXd layer::get_weights_biases_as_vec_col_maj

(

)

Returns the weights and the biases of the layers as a column vector. The order is the following: Weights of the first node, bias of the first node, weights of the first node, bias of the second node, etc.

get_weights_biases_as_vec_row_maj()

const Eigen::MatrixXd layer::get_weights_biases_as_vec_row_maj

(

)

Returns the weights and the biases of the layers as a row vector. The order is the following: Weights of the first node, bias of the first node, weights of the first node, bias of the second node, etc.

get_weights_cols()

int layer::get_weights_cols

(

)

Returns the number of columns of the weights matrix.

get_weights_rows()

int layer::get_weights_rows

(

)

Returns the number of rows of the weights matrix.

predict()

virtual Eigen::VectorXd layer::predict ( const Eigen::VectorXd &  input )

inlinevirtual

Computes the output of the layer given an Eigen::VectorXd as input.

Reimplemented in fc_layer_sg, fc_layer_sl, fc_layer_sp, and fc_layer_sm.

predict_batch()

virtual std::vector<Eigen::VectorXd> layer::predict_batch ( const std::vector< Eigen::VectorXd > &  input )

inlinevirtual

Computes the outputs of the layer given a vector<Eigen::VectorXd> as input.

Reimplemented in fc_layer_sg, fc_layer_sl, and fc_layer_sp.

set_bias()

void layer::set_bias	(	int	i,
		double	bias_
	)

Sets the bias of the i-th node.

set_biases() [1/2]

void layer::set_biases

(

const Eigen::VectorXd &

biases_

)

Sets the biases of the layer.

set_biases() [2/2]

void layer::set_biases

(

const std::vector< double > &

biases_

)

Sets the biases of the layer.

set_exp_max_cut()

void layer::set_exp_max_cut

(

double

exp_max_cut_

)

Set the exp_max_cut parameter to approximate \( f(x) = e^{-x} \) and \( f(x) = ln(1+e^{x}) \) for large values of the argument \( x \).

• For \( x \) above exp_max_cut approximates \( f(x) = e^{-x} \) with exp_zero_approx.
• For \( x \) above exp_max_cut approximates \( f(x) = ln(1+e^{x}) \) with \( x \).

set_exp_zero_approx()

void layer::set_exp_zero_approx

(

double

exp_zero_approx_

)

Set the exp_zero_approx parameter to approximate \( f(x) = e^{-x} \) and \( f(x) = ln(1+e^{x}) \) for large values of the argument \( x \).

• For \( x \) above exp_max_cut approximates \( f(x) = e^{-x} \) with exp_zero_approx.
• For \( x \) above exp_max_cut approximates \( f(x) = ln(1+e^{x}) \) with \( x \).

set_weight()

void layer::set_weight	(	int	i,
		int	j,
		double	weight_
	)

Sets the (i-th,j-th) weight of the layer.

set_weights()

void layer::set_weights

(

const Eigen::MatrixXd &

weights_

)

Sets the weights of the layer.

set_weights_biases()

void layer::set_weights_biases

(

Eigen::MatrixXd &

source

)

Sets the weights and the biases of the layer. The entries of the input (1 x N) matrix is the following: Weights of the first node, bias of the first node, weights of the first node, bias of the second node, etc.

set_weights_biases_compact()

void layer::set_weights_biases_compact

(

Eigen::MatrixXd &

source

)

Sets the weights and the biases of the layer, passing a matrix whose last column is the vector of the biases.

set_weights_biases_row_maj()

void layer::set_weights_biases_row_maj

(

Eigen::MatrixXd &

source

)

Sets the weights and the biases of the layer. The entries of the input (1 x N) matrix is the following: Weights of the first node, bias of the first node, weights of the first node, bias of the second node, etc.

transpose_weights()

void layer::transpose_weights

(

)

Transposes the weights matrix of the layer.

---

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

• layer.h
• layer.cpp