org.neuroph.nnet.comp.layer

Class CompetitiveLayer

java.lang.Object

org.neuroph.core.Layer

org.neuroph.nnet.comp.layer.CompetitiveLayer

All Implemented Interfaces:

Serializable, Iterable<Neuron>

public class CompetitiveLayer
extends Layer

Represents layer of competitive neurons, and provides methods for competition. TODO: competitive learning 3. training dw=n(i-w)

Author:

Zoran Sevarac

See Also:

Serialized Form

Field Summary

Fields inherited from class org.neuroph.core.Layer

neurons

Constructor Summary

Constructors

Constructor and Description
CompetitiveLayer(int neuronNum, NeuronProperties neuronProperties) Create an instance of CompetitiveLayer with the specified number of neurons with neuron properties

Method Summary

Modifier and Type	Method and Description
void	calculate() Performs calculaton for all neurons in this layer
int	getMaxIterations() Returns the maxIterations setting for this layer
CompetitiveNeuron	getWinner() Returns the winning neuron for this layer
void	setMaxIterations(int maxIterations) Sets max iterations for neurons to compete in this layer

Methods inherited from class org.neuroph.core.Layer

addNeuron, addNeuron, getLabel, getNeuronAt, getNeurons, getNeuronsCount, getParentNetwork, indexOf, initializeWeights, isEmpty, iterator, removeAllNeurons, removeNeuron, removeNeuronAt, reset, setLabel, setNeuron, setParentNetwork

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface java.lang.Iterable

forEach, spliterator

Constructor Detail

CompetitiveLayer

public CompetitiveLayer(int neuronNum,
                        NeuronProperties neuronProperties)

Create an instance of CompetitiveLayer with the specified number of neurons with neuron properties

Parameters:

neuronNum - neuron number in this layer

neuronProperties - properties for the nurons in this layer

Method Detail

calculate

public void calculate()

Performs calculaton for all neurons in this layer

Overrides:

calculate in class Layer

getWinner

public CompetitiveNeuron getWinner()

Returns the winning neuron for this layer

Returns:

winning neuron for this layer

getMaxIterations

public int getMaxIterations()

Returns the maxIterations setting for this layer

Returns:

maxIterations setting for this layer

setMaxIterations

public void setMaxIterations(int maxIterations)

Sets max iterations for neurons to compete in this layer

Parameters:

maxIterations - max iterations for neurons to compete in this layer