neuralpp::Layer Class Reference

Class for managing layers of neurons. More...

#include <neural++.hpp>

List of all members.

Public Member Functions
	Layer (size_t sz, double(*a)(double))
	Constructor.
	Layer (vector< Neuron > &neurons, double(*a)(double))
	Alternative constructor.
Neuron &	operator[] (size_t i) throw (NetworkIndexOutOfBoundsException)
	Redefinition for operator [].
void	link (Layer &l)
	It links a layer to another.
void	setProp (vector< double > &v)
	It sets a vector of propagation values to all its neurons.
void	setActv (vector< double > &v)
	It sets a vector of activation values to all its neurons.
void	propagate ()
	It propagates its activation values to the output layers.
size_t	size () const
Private Attributes
vector< Neuron >	elements
void(*	update_weights )()
double(*	actv_f )(double)

---

Detailed Description

Class for managing layers of neurons.

Don't use this class directly unless you know what you're doing, use NeuralNet instead

---

Constructor & Destructor Documentation

neuralpp::Layer::Layer	(	size_t	sz,
		double(*)(double)	a
	)

Constructor.

Parameters:

	sz	Size of the layer
	a	Activation function

neuralpp::Layer::Layer	(	vector< Neuron > &	neurons,
		double(*)(double)	a
	)

Alternative constructor.

It directly gets a vector of neurons to build the layer

Parameters:

	neurons	Vector of neurons to be included in the layer
	a	Activation function

---

Member Function Documentation

Neuron& neuralpp::Layer::operator[]

(

size_t

i

)

throw (NetworkIndexOutOfBoundsException)

Redefinition for operator [].

It gets the neuron at i

Parameters:

i

Index of the neuron to get in the layer

Returns:

Reference to the i-th neuron

void neuralpp::Layer::link

(

Layer &

l

)

It links a layer to another.

Parameters:

l

Layer to connect to the current as input layer

void neuralpp::Layer::setProp

(

vector< double > &

v

)

It sets a vector of propagation values to all its neurons.

Parameters:

v

Vector of values to write as propagation values

void neuralpp::Layer::setActv

(

vector< double > &

v

)

It sets a vector of activation values to all its neurons.

Parameters:

v

Vector of values to write as activation values

void neuralpp::Layer::propagate

(

)

It propagates its activation values to the output layers.

size_t neuralpp::Layer::size

(

)

const

Returns:

Number of neurons in the layer

---

Member Data Documentation

vector<Neuron> neuralpp::Layer::elements [private]

void(* neuralpp::Layer::update_weights)() [private]

double(* neuralpp::Layer::actv_f)(double) [private]

---

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

• neural++.hpp