AimsMLPNeuron Class Reference

The class that describes MLP neuron. More...

#include <aims/neuralnet/multilayerperceptron.h>

Collaboration diagram for AimsMLPNeuron:

Public Member Functions
Constructor and Destructor
	AimsMLPNeuron (int ninputs)
	Constructor. More...
virtual	~AimsMLPNeuron ()
	Destructor deletes allocated data. More...
Methods
int	nInputs () const
	Return the number of inputs. More...
float	output () const
	Return the actual output. More...
float	activation () const
	Return the activation. More...
float	error () const
	Return the error. More...
float	deltaW (int i) const
	Return the variation of weights. More...
float	weight (int i) const
	Return the ieme weight. More...
void	setWeight (const AimsData< float > &weight)
	Set the weights from weight vector. More...
void	forward (const AimsData< float > &input)
	Forward propagation. More...
void	evaluateError (float target)
	Error evaluation. More...
void	backPropagation (const AimsData< float > &nexterror, const AimsData< float > &nextweight)
	Gradient back propagation. More...
void	adjust (const AimsData< float > &input, float learningrate, float momentum)
	Modification of the weights. More...

Protected Attributes
Data
int	_nInputs
	Number of inputs. More...
float	_output
	Floating output. More...
float	_activation
	Activation value (before entering sigmoid function) More...
float	_error
	Error between desired and actual value. More...
AimsData< float > *	_deltaW
	Weight variation data. More...
AimsData< float > *	_weight
	Weight data. More...

Detailed Description

The class that describes MLP neuron.

Definition at line 47 of file multilayerperceptron.h.

Constructor & Destructor Documentation

AimsMLPNeuron()

AimsMLPNeuron::AimsMLPNeuron

(

int

ninputs

)

Constructor.

Parameters

ninputs

number of inputs of the neuron

~AimsMLPNeuron()

virtual AimsMLPNeuron::~AimsMLPNeuron ( )

virtual

Destructor deletes allocated data.

Member Function Documentation

activation()

float AimsMLPNeuron::activation

(

)

const

Return the activation.

adjust()

void AimsMLPNeuron::adjust	(	const AimsData< float > &	input,
		float	learningrate,
		float	momentum
	)

Modification of the weights.

backPropagation()

void AimsMLPNeuron::backPropagation	(	const AimsData< float > &	nexterror,
		const AimsData< float > &	nextweight
	)

Gradient back propagation.

deltaW()

float AimsMLPNeuron::deltaW

(

int

i

)

const

Return the variation of weights.

error()

float AimsMLPNeuron::error

(

)

const

Return the error.

evaluateError()

void AimsMLPNeuron::evaluateError

(

float

target

)

Error evaluation.

forward()

void AimsMLPNeuron::forward

(

const AimsData< float > &

input

)

Forward propagation.

nInputs()

int AimsMLPNeuron::nInputs

(

)

const

Return the number of inputs.

output()

float AimsMLPNeuron::output

(

)

const

Return the actual output.

setWeight()

void AimsMLPNeuron::setWeight

(

const AimsData< float > &

weight

)

Set the weights from weight vector.

weight()

float AimsMLPNeuron::weight

(

int

i

)

const

Return the ieme weight.

Member Data Documentation

_activation

float AimsMLPNeuron::_activation

protected

Activation value (before entering sigmoid function)

Definition at line 56 of file multilayerperceptron.h.

_deltaW

AimsData<float>* AimsMLPNeuron::_deltaW

protected

Weight variation data.

Definition at line 60 of file multilayerperceptron.h.

_error

float AimsMLPNeuron::_error

protected

Error between desired and actual value.

Definition at line 58 of file multilayerperceptron.h.

_nInputs

int AimsMLPNeuron::_nInputs

protected

Number of inputs.

Definition at line 52 of file multilayerperceptron.h.

_output

float AimsMLPNeuron::_output

protected

Floating output.

Definition at line 54 of file multilayerperceptron.h.

_weight

AimsData<float>* AimsMLPNeuron::_weight

protected

Weight data.

Definition at line 62 of file multilayerperceptron.h.

---

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

• aims/neuralnet/multilayerperceptron.h