smile.vq

Class GrowingNeuralGas

java.lang.Object

smile.vq.GrowingNeuralGas

All Implemented Interfaces:

Clustering<double[]>

public class GrowingNeuralGas
extends java.lang.Object
implements Clustering<double[]>

Growing Neural Gas. As an extension of Neural Gas, Growing Neural Gas can add and delete nodes during algorithm execution. The growth mechanism is based on growing cell structures and competitive Hebbian learning.

Compared to Neural Gas, GNG has the following distinctions:

• The system has the ability to add and delete nodes.
• Local Error measurements are noted at each step helping it to locally insert/delete nodes.
• Edges are connected between nodes, so a sufficiently old edges is deleted. Such edges are intended place holders for localized data distribution.
• Such edges also help to locate distinct clusters (those clusters are not connected by edges).

References

1. B. Fritzke. A growing neural gas network learns topologies. NIPS, 1995.

See Also:

KMeans, NeuralGas, NeuralMap

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	GrowingNeuralGas.Neuron The neuron vertex in the growing neural gas network.

Field Summary

Fields inherited from interface smile.clustering.Clustering

OUTLIER

Constructor Summary

Constructors

Constructor and Description
GrowingNeuralGas(int d) Constructor.
GrowingNeuralGas(int d, double epsBest, double epsNeighbor, int maxEdgeAge, int lambda, double alpha, double beta) Constructor.

Method Summary

Modifier and Type	Method and Description
GrowingNeuralGas.Neuron[]	neurons() Returns the neurons in the network.
void	partition(int k) Clustering neurons into k clusters.
int	predict(double[] x) Cluster a new instance to the nearest neuron.
void	update(double[] x) Update the Neural Gas with a new signal.

Methods inherited from class java.lang.Object

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

Constructor Detail

GrowingNeuralGas

public GrowingNeuralGas(int d)

Constructor.

Parameters:

d - the dimensionality of signals.

GrowingNeuralGas

public GrowingNeuralGas(int d,
                        double epsBest,
                        double epsNeighbor,
                        int maxEdgeAge,
                        int lambda,
                        double alpha,
                        double beta)

Constructor.

Parameters:

d - the dimensionality of signals.

epsBest - the fraction to update nearest neuron.

epsNeighbor - the fraction to update neighbors of nearest neuron.

maxEdgeAge - the maximum age of edges.

lambda - if the number of input signals so far is an integer multiple of lambda, insert a new neuron.

alpha - decrease error variables by multiplying them with alpha during inserting a new neuron.

beta - decrease all error variables by multiply them with beta.

Method Detail

neurons

public GrowingNeuralGas.Neuron[] neurons()

Returns the neurons in the network.

Returns:

the neurons in the network.

update

public void update(double[] x)

Update the Neural Gas with a new signal.

partition

public void partition(int k)

Clustering neurons into k clusters.

Parameters:

k - the number of clusters.

predict

public int predict(double[] x)

Cluster a new instance to the nearest neuron.

Specified by:

predict in interface Clustering<double[]>

Parameters:

x - a new instance.

Returns:

the cluster label. If the method partition() was called, this is the cluster id of nearest neuron. Otherwise, it is just the index of neuron.