org.simbrain.network.subnetworks

Class SOMNetwork

java.lang.Object

org.simbrain.network.groups.Group

org.simbrain.network.groups.Subnetwork

org.simbrain.network.subnetworks.SOMNetwork

All Implemented Interfaces:

Trainable

public class SOMNetwork
extends Subnetwork
implements Trainable

SOMNetwork is a small network encompassing an SOM group. An input layer and input data have been added so that the SOM can be easily trained using existing Simbrain GUI tools

Author:

Jeff Yoshimi

Constructor Summary

Constructors

Constructor and Description
SOMNetwork(Network net, int numSOMNeurons, int numInputNeurons, java.awt.geom.Point2D initialPosition) Construct an SOM Network.

Method Summary

Modifier and Type	Method and Description
NeuronGroup	getInputLayer()
java.util.List<Neuron>	getInputNeurons() Returns the list of input neurons.
Group	getNetwork() Returns a reference to the subnetwork or synapse group being trained.
java.util.List<Neuron>	getOutputNeurons() Returns the list of output neurons.
SOMGroup	getSom()
TrainingSet	getTrainingSet() Returns the the training set, which contains input and target data.
void	initNetwork() Initialize the network.
void	layoutNetwork() Set the layout of the network.

Methods inherited from class org.simbrain.network.groups.Subnetwork

addAndLabelSynapseGroup, addNeuronGroup, addRowToTrainingSet, addSynapseGroup, clearActivations, connectNeuronGroups, connectNeuronGroups, connectNeuronGroups, delete, displayNeuronGroups, getEnabled, getFlatNeuronList, getFlatSynapseList, getIndexOfNeuronGroup, getLongDescription, getModifiableNeuronList, getNeuronGroup, getNeuronGroup, getNeuronGroupByLabel, getNeuronGroupCount, getNeuronGroupList, getNeuronGroupsAsList, getSynapseGroup, getSynapseGroup, getSynapseGroupByLabel, getSynapseGroupCount, getSynapseGroupList, getUpdateMethodDesecription, isEmpty, recursivelySetIds, removeNeuronGroup, removeSynapseGroup, setDisplayNeuronGroups, setEnabled, size, toString, update

Methods inherited from class org.simbrain.network.groups.Group

getId, getLabel, getParentGroup, getParentNetwork, getStateInfo, hasParentGroup, isMarkedForDeletion, isTopLevelGroup, setId, setLabel, setMarkedForDeletion, setParentGroup, setStateInfo

Methods inherited from class java.lang.Object

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

Constructor Detail

SOMNetwork

public SOMNetwork(Network net,
                  int numSOMNeurons,
                  int numInputNeurons,
                  java.awt.geom.Point2D initialPosition)

Construct an SOM Network.

Parameters:

net - parent network. Set to null when this is used simply as a holder for param values.

numSOMNeurons - number of neurons in the SOM layer

numInputNeurons - number of neurons in the input layer

initialPosition - bottom corner where network will be placed.

Method Detail

layoutNetwork

public void layoutNetwork()

Set the layout of the network.

getInputNeurons

public java.util.List<Neuron> getInputNeurons()

Description copied from interface: Trainable

Returns the list of input neurons.

Specified by:

getInputNeurons in interface Trainable

Returns:

the list of input neurons.

getOutputNeurons

public java.util.List<Neuron> getOutputNeurons()

Description copied from interface: Trainable

Returns the list of output neurons.

Specified by:

getOutputNeurons in interface Trainable

Returns:

list of output neurons

getTrainingSet

public TrainingSet getTrainingSet()

Description copied from interface: Trainable

Returns the the training set, which contains input and target data.

Specified by:

getTrainingSet in interface Trainable

Returns:

the training set.

initNetwork

public void initNetwork()

Description copied from interface: Trainable

Initialize the network. E.g. used before a training run for SRN's to clear activations.

Specified by:

initNetwork in interface Trainable

getSom

public SOMGroup getSom()

Returns:

the som

getInputLayer

public NeuronGroup getInputLayer()

Returns:

the inputLayer

getNetwork

public Group getNetwork()

Description copied from interface: Trainable

Returns a reference to the subnetwork or synapse group being trained.

Specified by:

getNetwork in interface Trainable

Returns:

the network being trained.