org.simbrain.network.subnetworks

Class WinnerTakeAll

java.lang.Object

org.simbrain.network.groups.Group

org.simbrain.network.groups.NeuronGroup

org.simbrain.network.subnetworks.WinnerTakeAll

All Implemented Interfaces:

CopyableGroup<NeuronGroup>

public class WinnerTakeAll
extends NeuronGroup

WinnerTakeAll.The neuron with the highest weighted input in a winner-take-all network takes on an upper value, all other neurons take on the lower value. In case of a tie the node which wins is arbitrary (the first in an internally maintained list).

Field Summary

Fields inherited from class org.simbrain.network.groups.NeuronGroup

DEFAULT_GROUP_SIZE, DEFAULT_LAYOUT, FLUSH_FREQUENCY

Constructor Summary

Constructors

Constructor and Description
WinnerTakeAll(Network root, int numNeurons) Creates a new winner take all network.
WinnerTakeAll(Network newRoot, WinnerTakeAll oldNet) Copy constructor.

Method Summary

Modifier and Type	Method and Description
WinnerTakeAll	deepCopy(Network newNetwork) Returns a deep copy of a copyable group using the same root network as the original.
double	getLoseValue()
int	getNumUnits()
double	getRandomProb()
java.lang.String	getTypeDescription() Return a human-readable name for this type of neuron group.
double	getWinValue()
boolean	isUseRandom()
void	setLoseValue(double loseValue)
void	setRandomProb(double randomProb)
void	setUseRandom(boolean useRandom)
void	setWinValue(double winValue)
void	update() Updates all the neurons in the neuron group according to their NeuronUpdateRule(s).

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

addIncomingSg, addNeuron, addNeuron, addOutgoingSg, applyInputs, applyLayout, applyLayout, clearActivations, clearNeuronList, containsAsIncoming, containsAsOutgoing, containsNeuron, copyActivations, delete, forceSetActivationLevels, forceSetActivations, getActivations, getBetweenNeuronInterval, getBiases, getCenterX, getCenterY, getExternalActivations, getFourCorners, getGridThreshold, getHeight, getIncomingSgs, getIncomingWeights, getLabelsOfActiveNeurons, getLayout, getMaxDim, getMaxX, getMaxY, getMinX, getMinY, getMostActiveNeuron, getNeuronList, getNeuronsInRadius, getNeuronType, getNumSubSamples, getOutgoingSg, getOutgoingWeights, getPosition, getSpikeIndexes, getTestData, getUpdateMethodDesecription, getWidth, inFanInOfSomeNode, isAllClamped, isAllUnclamped, isEmpty, isInputMode, isRecordAsSpikes, isRecording, isSpikingNeuronGroup, isUseSubSampling, offset, printActivations, prune, randomize, randomizeBiases, randomizeIncomingWeights, randomizeOutgoingWeights, readNextInputs, removeIncomingSg, removeNeuron, removeOutgoingSg, resetSubsamplingIndices, setActivationLevels, setActivations, setBetweenNeuronInterval, setClamped, setGridThreshold, setIncrement, setInputMode, setInputValues, setLayout, setLayoutBasedOnSize, setLayoutBasedOnSize, setLocation, setLowerBound, setNeuronType, setNeuronType, setNumSubSamples, setRecordAsSpikes, setSpikingNeuronGroup, setTestData, setUpperBound, setUseSubSampling, setXYZCoordinatesFromFile, size, startRecording, stopRecording, testAndSetIfSpiking, toString, writeActsToFile

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

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

Methods inherited from class java.lang.Object

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

Constructor Detail

WinnerTakeAll

public WinnerTakeAll(Network newRoot,
                     WinnerTakeAll oldNet)

Copy constructor.

Parameters:

newRoot - new root net

oldNet - old network

WinnerTakeAll

public WinnerTakeAll(Network root,
                     int numNeurons)

Creates a new winner take all network.

Parameters:

root - the network containing this subnetwork

numNeurons - Number of neurons in new network

Method Detail

deepCopy

public WinnerTakeAll deepCopy(Network newNetwork)

Description copied from interface: CopyableGroup

Returns a deep copy of a copyable group using the same root network as the original.

Specified by:

deepCopy in interface CopyableGroup<NeuronGroup>

Overrides:

deepCopy in class NeuronGroup

Parameters:

newNetwork - the parent network for this group, potentially different from the original (used when copying and pasting from one network to another)

Returns:

a deep copy of a group

getTypeDescription

public java.lang.String getTypeDescription()

Description copied from class: NeuronGroup

Return a human-readable name for this type of neuron group. Subclasses should override this. Used in the Gui for various purposes.

Overrides:

getTypeDescription in class NeuronGroup

Returns:

the name of this type of neuron group.

update

public void update()

Description copied from class: NeuronGroup

Updates all the neurons in the neuron group according to their NeuronUpdateRule(s). If the group is in input mode reads in the next set of values from the input table and sets the neuron values accordingly.

Overrides:

update in class NeuronGroup

getLoseValue

public double getLoseValue()

Returns:

Returns the loseValue.

setLoseValue

public void setLoseValue(double loseValue)

Parameters:

loseValue - The loseValue to set.

getWinValue

public double getWinValue()

Returns:

Returns the winValue.

setWinValue

public void setWinValue(double winValue)

Parameters:

winValue - The winValue to set.

getNumUnits

public int getNumUnits()

Returns:

Number of neurons.

isUseRandom

public boolean isUseRandom()

Returns:

the useRandom

setUseRandom

public void setUseRandom(boolean useRandom)

Parameters:

useRandom - the useRandom to set

getRandomProb

public double getRandomProb()

Returns:

the randomProb

setRandomProb

public void setRandomProb(double randomProb)

Parameters:

randomProb - the randomProb to set