---

PerceptronNeuron Class Reference

#include <PerceptronNeuron.h>

List of all members.

Public Member Functions
	PerceptronNeuron (unsigned int in_layer_num)
double	getDelta (void)
void	setDelta (double newval)
double	getTheta (void)
void	setTheta (double newval)
double	getThetaDiff (void)
void	initializeWeightings (unsigned int succ_count)
void	resetWeights (void)
void	resetWeightDiffs (void)
void	resetDiffs (void)
void	postprocessWeight (PerceptronNeuron *succ, double epsilon, double weight_decay, double momterm)
void	postprocessTheta (double epsilon, double weight_decay, double momterm)
void	update (void)
Public Attributes
unsigned int	num
double	input
double	output
vector< double >	weight
vector< double >	weight_diff
Protected Attributes
double	delta
double	theta
double	theta_diff
double	theta_diff_last
vector< double >	weight_diff_last

---

Detailed Description

Represent one neuron within a layer of the neural network.

---

Constructor & Destructor Documentation

PerceptronNeuron::PerceptronNeuron (  unsigned int    in_layer_num )

Main constructor. Parameters: in_layer_num  number of neuron within its layer.

---

Member Function Documentation

double PerceptronNeuron::getDelta (  void    )  [inline]

Getter function for the delta variable.

double PerceptronNeuron::getTheta (  void    )  [inline]

Getter function for theta parameter.

double PerceptronNeuron::getThetaDiff (  void    )  [inline]

Getter for the difference calculated for the theta parameter.

void PerceptronNeuron::initializeWeightings (  unsigned int    succ_count )

Initialize the weightings vectors used for each neuron to zero. Parameters: succ_count  number of successor neurons to this neuron.

void PerceptronNeuron::postprocessTheta (  double    epsilon, double    weight_decay, double    momterm )

Theta postprocess algorithm. Assign the theta differences to this neuron. Parameters: epsilon  Learning parameter. weight_decay  Weight decay factor. momterm  Momentum term factor.

void PerceptronNeuron::postprocessWeight (  PerceptronNeuron *    succ, double    epsilon, double    weight_decay, double    momterm )

Weighting postprocess algorithm. Assign the weight differences to this neuron. Note that the assignment is done by adding the new delta value to the current one. Hence, both batch- and online learning can use this function. For online-learning the values must be resetted after each update using the resetWeightDiffs method. Also, only one weighting difference is calculated at a time. The computation of all differences is scheduled by PerceptronLayer::postprocess. Parameters: succ  Successor neuron to the current neuron. epsilon  Learning parameter. weight_decay  Weight decay factor. momterm  Momentum term factor. See also: resetWeightDiffs ()

void PerceptronNeuron::resetDiffs (  void    )

Reset all learned differences.

void PerceptronNeuron::resetWeightDiffs (  void    )

Reset all weight deltas to zero.

void PerceptronNeuron::resetWeights (  void    )

Reset all weightings to zero.

void PerceptronNeuron::setDelta (  double    newval )  [inline]

Setter function for the delta variable. Parameters: newval  New value to be assigned to delta.

void PerceptronNeuron::setTheta (  double    newval )  [inline]

Setter function for theta parameter.

void PerceptronNeuron::update (  void    )

Update algorithm. Update weightings and theta parameter by the values calculated in the postprocess step.

---

Member Data Documentation

double PerceptronNeuron::delta [protected]

Errorsignal, computed by the backpropagation algorithm. Used to compute the deltas for both the weightings and the sensitivity parameter

double PerceptronNeuron::input

Input signal level for this node, .

unsigned int PerceptronNeuron::num

Counter within the current layer (top = 0)

double PerceptronNeuron::output

Output signal level for this node, .

double PerceptronNeuron::theta [protected]

Sensitivity parameter to the activation function

double PerceptronNeuron::theta_diff [protected]

Delta-value for the sensitivity, calculated by the Processing algorithm, used to update theta within the Update algorithm

double PerceptronNeuron::theta_diff_last [protected]

The previous theta difference, used for momentum term calculation.

vector<double> PerceptronNeuron::weight

Weightings to neurons in the next layer. Hence, the size of the vector must equal the number of neurons in the next layer

vector<double> PerceptronNeuron::weight_diff

Delta-value for the individual weightings the node has to its successor nodes. Computed by the Processing algorithm Note this is within the public space due to the from-file constructor of PerceptronNetwork, which push_back's zeroes here.

vector<double> PerceptronNeuron::weight_diff_last [protected]

The previous weight differences, used for momentum term.

---

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

• PerceptronNeuron.h
• PerceptronNeuron.cpp

---