---

PerceptronLayer Class Reference

#include <PerceptronLayer.h>

List of all members.

Public Member Functions
	PerceptronLayer (unsigned int neuron_count, const ActivationFunction *fact)
	~PerceptronLayer (void)
	PerceptronLayer (PerceptronLayer &source)
void	randomizeParameters (PerceptronLayer *succ, const RandomFunction *weight_func, const RandomFunction *theta_func)
void	resetDiffs (void)
void	setActivationFunction (const ActivationFunction *fact)
const ActivationFunction *	getActivationFunction (void) const
void	propagate (PerceptronLayer *pred)
void	backpropagate (PerceptronLayer *succ, vector< double > &output_optimal, double opt_tolerance)
void	postprocess (PerceptronLayer *succ, double epsilon, double weight_decay, double momterm)
void	update (void)
Public Attributes
PerceptronLayerType	type
vector< PerceptronNeuron * >	neurons
Protected Attributes
const ActivationFunction *	fact

---

Detailed Description

One layer within the perceptron network.

Most algorithm related calculation is done at the layer level.

---

Constructor & Destructor Documentation

PerceptronLayer::PerceptronLayer (  unsigned int    neuron_count, const ActivationFunction *    fact )

PerceptronLayer constructor, creating a layer with neuron_count number of neurons. Parameters: neuron_count  Number of neurons within this layer. fact  Activation function to use for this layer.

PerceptronLayer::~PerceptronLayer (  void    )

PerceptronLayer destructor, mainly removing all the subneurons within this layer.

PerceptronLayer::PerceptronLayer (  PerceptronLayer &    source )

Copy constructor. Parameters: source  Source object to be copied.

---

Member Function Documentation

void PerceptronLayer::backpropagate (  PerceptronLayer *    succ, vector< double > &    output_optimal, double    opt_tolerance )

Backpropagation algorithm. Compute the delta value for all neurons within this layer. Parameters: succ  Succeeding layer to this one, can be NULL. output_optimal  Optimal expected output for the last layer (output). opt_tolerance  The optimal difference tolerance parameter.

const ActivationFunction * PerceptronLayer::getActivationFunction (  void    )  const

Getter for the activation function.

void PerceptronLayer::postprocess (  PerceptronLayer *    succ, double    epsilon, double    weight_decay, double    momterm )

Postprocess algorithm for a single layer. Parameters: succ  Successor layer to this one, or NULL if it is the last. epsilon  Learning parameter. weight_decay  Weight decay factor. momterm  Momentum term factor.

void PerceptronLayer::propagate (  PerceptronLayer *    pred )

Forward propagation algorithm. The input and output signals of this layer is calculated from the output signals of the pred layer. Parameters: pred  the layer before this one, can be NULL.

void PerceptronLayer::randomizeParameters (  PerceptronLayer *    succ, const RandomFunction *    weight_func, const RandomFunction *    theta_func )

Network randomization functions. Randomize variable network parameters: weightings and theta values. Use individual functions for greater customizeability. Parameters: succ  Succeeding layer in network. Must be non-NULL. weight_func  Function to generate weighting parameters. theta_func  Function to generate theta values.

void PerceptronLayer::resetDiffs (  void    )

Reset functions for learned differences. This function resets all parameters that are learned by the backpropagation and postprocess algorithms. It has to be called after an update has been made. This way, both online- and batch-learning can be implemented.

void PerceptronLayer::setActivationFunction (  const ActivationFunction *    fact )

Setter for the activation function. Parameters: fact  Activation function to use for this layer.

void PerceptronLayer::update (  void    )

Update algorithm for a single layer.

---

Member Data Documentation

const ActivationFunction* PerceptronLayer::fact [protected]

Activation function and its derivate. Used for both propagation and backpropagation. Must be set and can be different for each layer.

vector<PerceptronNeuron *> PerceptronLayer::neurons

Every layer contains at least one neuron. This is the list of neurons within this layer.

PerceptronLayerType PerceptronLayer::type

Type of the layer within the network. The input layer is always the first, the output layer the last layer in the network. Every other layer must be a hidden layer.

---

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

• PerceptronLayer.h
• PerceptronLayer.cpp

---