SOMGroup (Simbrain API)

java.lang.Object
- org.simbrain.network.groups.Group
- - org.simbrain.network.groups.NeuronGroup
  - - org.simbrain.network.subnetworks.SOMGroup

All Implemented Interfaces:

CopyableGroup<NeuronGroup>
```
public class SOMGroup
extends NeuronGroup
```
SOM implements a Self-Organizing Map network.

Author:

William B. St. Clair, Jeff Yoshimi

Field Summary

Fields
Modifier and Type	Field and Description
`static double`	`DEFAULT_ALPHA` Default alpha.
`static int`	`DEFAULT_BATCH_SIZE` Default batchSize.
`static double`	`DEFAULT_DECAY_RATE` The default alphaDecayRate.
`static double`	`DEFAULT_INIT_NSIZE` Default initial neighborhood size.
`static Layout`	`DEFAULT_LAYOUT` Default layout for neuron groups.
`static double`	`DEFAULT_NEIGHBORHOOD_DECAY_AMOUNT` The default neighborhoodDecayAmount.

Fields inherited from class org.simbrain.network.groups.NeuronGroup
DEFAULT_GROUP_SIZE, FLUSH_FREQUENCY

Constructor Summary

Constructors
Constructor and Description
`SOMGroup(Network root, int numNeurons)` Constructs an SOM network with specified number of neurons.
`SOMGroup(Network newRoot, SOMGroup oldNet)` Copy constructor

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`SOMGroup`	`deepCopy()`
`double`	`getAlpha()` get Alpha.
`double`	`getAlphaDecayRate()` Get alphaDecayRate.
`int`	`getBatchSize()` Get the Batch Size.
`double`	`getInitAlpha()` get Initial Alpha.
`double`	`getInitNeighborhoodSize()` Get the initial neighborhoodsize.
`double`	`getNeighborhoodDecayAmount()` Get neighborhoodDecayAmount.
`double`	`getNeighborhoodSize()` Get the current neighborhood size.
`int`	`getNumNeurons()` Get the number of neurons.
`java.lang.String`	`getTypeDescription()` Return a human-readable name for this type of neuron group.
`void`	`randomizeIncomingWeights()` Randomize all weights coming in to this network.
`void`	`recall()` Pushes the weight values of an SOM neuron onto the input neurons.
`void`	`reset()` Resets SOM Network to initial values.
`void`	`setAlphaDecayRate(double alphaDecayRate)` Set alphaDecayRate.
`void`	`setBatchSize(int batchSize)` Set the Batch Size.
`void`	`setInitAlpha(double initAlpha)` Set the initial value for alpha.
`void`	`setInitNeighborhoodSize(double initNeighborhoodSize)` Set the initial neighborhood size.
`void`	`setNeighborhoodDecayAmount(double neighborhoodDecayAmount)` Set neighborhoodDecayAmount.
`void`	`setNumNeurons(int numNeurons)` Set the number of neurons.
`void`	`update()` Update the network.

Methods inherited from class org.simbrain.network.groups.NeuronGroup
addIncomingSg, addNeuron, addNeuron, addOutgoingSg, applyInputs, applyLayout, applyLayout, clearActivations, clearNeuronList, containsAsIncoming, containsAsOutgoing, containsNeuron, copyActivations, deepCopy, 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, 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

- Field Detail
  - DEFAULT_ALPHA
```
public static final double DEFAULT_ALPHA
```
    Default alpha.
    
    See Also:
    
    Constant Field Values
  - DEFAULT_INIT_NSIZE
```
public static final double DEFAULT_INIT_NSIZE
```
    Default initial neighborhood size.
    
    See Also:
    
    Constant Field Values
  - DEFAULT_BATCH_SIZE
```
public static final int DEFAULT_BATCH_SIZE
```
    Default batchSize.
    
    See Also:
    
    Constant Field Values
  - DEFAULT_DECAY_RATE
```
public static final double DEFAULT_DECAY_RATE
```
    The default alphaDecayRate.
    
    See Also:
    
    Constant Field Values
  - DEFAULT_NEIGHBORHOOD_DECAY_AMOUNT
```
public static final double DEFAULT_NEIGHBORHOOD_DECAY_AMOUNT
```
    The default neighborhoodDecayAmount.
    
    See Also:
    
    Constant Field Values
  - DEFAULT_LAYOUT
```
public static final Layout DEFAULT_LAYOUT
```
    Default layout for neuron groups. Used to set layout defaults in SOM Creation dialog. Overrides superclass DEFAULT_LAYOUT.
- Constructor Detail
  - SOMGroup
```
public SOMGroup(Network root,
                int numNeurons)
```
    Constructs an SOM network with specified number of neurons.
    
    Parameters:
    
    numNeurons - size of this network in neurons
    
    root - reference to Network.
  - SOMGroup
```
public SOMGroup(Network newRoot,
                SOMGroup oldNet)
```
    Copy constructor
    
    Parameters:
    
    newRoot -
    
    oldNet -
- Method Detail
  - deepCopy
```
public SOMGroup deepCopy()
```
  - 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.
  - randomizeIncomingWeights
```
public void randomizeIncomingWeights()
```
    Randomize all weights coming in to this network. The weights will be between 0 and the upper bound of each synapse.
    
    Overrides:
    
    randomizeIncomingWeights in class NeuronGroup
  - recall
```
public void recall()
```
    Pushes the weight values of an SOM neuron onto the input neurons.
  - reset
```
public void reset()
```
    Resets SOM Network to initial values.
  - update
```
public void update()
```
    Update the network. This method has the following structure: If all weights are clamped, return. Determine the winner by finding which of the SOM neurons is closest to the input vector. Update the winning neuron and it's neighborhood. The update algorithm accounts for all possible arrangements of the SOM network. - When the neuron is outside of the neighborhood. - When the neuron is within the the neighborhood. Including the current vector, if the total number of vectors analyzed during the current iteration is equal to the total number of vectors to be analyzed, update the network parameters and count one full iteration. Else the network must be in recallMode. If all neurons are clamped, return. Find the SOM neuron with highest activation. Set the activations of input neurons according to the SOM weights.
    
    Overrides:
    
    update in class NeuronGroup
  - getAlpha
```
public double getAlpha()
```
    get Alpha.
    
    Returns:
    
    alpha
  - getAlphaDecayRate
```
public double getAlphaDecayRate()
```
    Get alphaDecayRate.
    
    Returns:
    
    alphaDecayRate
  - getBatchSize
```
public int getBatchSize()
```
    Get the Batch Size.
    
    Returns:
    
    batchSize
  - getInitAlpha
```
public double getInitAlpha()
```
    get Initial Alpha.
    
    Returns:
    
    initAlpha
  - getInitNeighborhoodSize
```
public double getInitNeighborhoodSize()
```
    Get the initial neighborhoodsize.
    
    Returns:
    
    initNeighborhoodSize
  - getNeighborhoodDecayAmount
```
public double getNeighborhoodDecayAmount()
```
    Get neighborhoodDecayAmount.
    
    Returns:
    
    neighborhoodDecayAmount
  - getNeighborhoodSize
```
public double getNeighborhoodSize()
```
    Get the current neighborhood size.
    
    Returns:
    
    neighborhoodSize
  - getNumNeurons
```
public int getNumNeurons()
```
    Get the number of neurons.
    
    Returns:
    
    numNeurons
  - setAlphaDecayRate
```
public void setAlphaDecayRate(double alphaDecayRate)
```
    Set alphaDecayRate.
    
    Parameters:
    
    alphaDecayRate - decay rate
  - setBatchSize
```
public void setBatchSize(int batchSize)
```
    Set the Batch Size.
    
    Parameters:
    
    batchSize - Batch Size
  - setInitAlpha
```
public void setInitAlpha(double initAlpha)
```
    Set the initial value for alpha. Resets SOM if new.
    
    Parameters:
    
    initAlpha - initial alpha
  - setInitNeighborhoodSize
```
public void setInitNeighborhoodSize(double initNeighborhoodSize)
```
    Set the initial neighborhood size.
    
    Parameters:
    
    initNeighborhoodSize - initial neighborhood size Resets SOM if new.
  - setNeighborhoodDecayAmount
```
public void setNeighborhoodDecayAmount(double neighborhoodDecayAmount)
```
    Set neighborhoodDecayAmount.
    
    Parameters:
    
    neighborhoodDecayAmount - decay amount
  - setNumNeurons
```
public void setNumNeurons(int numNeurons)
```
    Set the number of neurons.
    
    Parameters:
    
    numNeurons - number of neurons.

Class SOMGroup

Field Summary

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

Constructor Summary

Method Summary

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

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

Methods inherited from class java.lang.Object

Field Detail

DEFAULT_ALPHA

DEFAULT_INIT_NSIZE

DEFAULT_BATCH_SIZE

DEFAULT_DECAY_RATE

DEFAULT_NEIGHBORHOOD_DECAY_AMOUNT

DEFAULT_LAYOUT

Constructor Detail

SOMGroup

SOMGroup

Method Detail

deepCopy

getTypeDescription

randomizeIncomingWeights

recall

reset

update

getAlpha

getAlphaDecayRate

getBatchSize

getInitAlpha

getInitNeighborhoodSize

getNeighborhoodDecayAmount

getNeighborhoodSize

getNumNeurons

setAlphaDecayRate

setBatchSize

setInitAlpha

setInitNeighborhoodSize

setNeighborhoodDecayAmount

setNumNeurons