org.apache.commons.math3.ml.neuralnet.oned

Class NeuronString

java.lang.Object

org.apache.commons.math3.ml.neuralnet.oned.NeuronString

All Implemented Interfaces:

java.io.Serializable

public class NeuronString
extends java.lang.Object
implements java.io.Serializable

Neural network with the topology of a one-dimensional line. Each neuron defines one point on the line.

Since:

3.3

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
private static class	NeuronString.SerializationProxy Serialization.

Field Summary

Fields

Modifier and Type	Field and Description
private long[]	identifiers Mapping of the 1D coordinate to the neuron identifiers (attributed by the network instance).
private Network	network Underlying network.
private static long	serialVersionUID Serial version ID
private int	size Number of neurons.
private boolean	wrap Wrap.

Constructor Summary

Constructors

Constructor and Description
NeuronString(boolean wrap, double[][] featuresList) Constructor with restricted access, solely used for deserialization.
NeuronString(int num, boolean wrap, FeatureInitializer[] featureInit) Creates a one-dimensional network: Each neuron not located on the border of the mesh has two neurons linked to it.

Method Summary

Methods

Modifier and Type	Method and Description
private void	createLinks() Creates the neighbour relationships between neurons.
double[]	getFeatures(int i) Retrieves the features set from the neuron at location i in the map.
Network	getNetwork() Retrieves the underlying network.
int	getSize() Gets the number of neurons.
private void	readObject(java.io.ObjectInputStream in) Prevents proxy bypass.
private java.lang.Object	writeReplace() Custom serialization.

Methods inherited from class java.lang.Object

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

Field Detail

serialVersionUID

private static final long serialVersionUID

Serial version ID

See Also:

Constant Field Values

network

private final Network network

Underlying network.

size

private final int size

Number of neurons.

wrap

private final boolean wrap

Wrap.

identifiers

private final long[] identifiers

Mapping of the 1D coordinate to the neuron identifiers (attributed by the network instance).

Constructor Detail

NeuronString

NeuronString(boolean wrap,
            double[][] featuresList)

Constructor with restricted access, solely used for deserialization.

Parameters:

wrap - Whether to wrap the dimension (i.e the first and last neurons will be linked together).

featuresList - Arrays that will initialize the features sets of the network's neurons.

Throws:

NumberIsTooSmallException - if num < 2.

NeuronString

public NeuronString(int num,
            boolean wrap,
            FeatureInitializer[] featureInit)

Creates a one-dimensional network: Each neuron not located on the border of the mesh has two neurons linked to it.
The links are bi-directional. Neurons created successively are neighbours (i.e. there are links between them).
The topology of the network can also be a circle (if the dimension is wrapped).

Parameters:

num - Number of neurons.

wrap - Whether to wrap the dimension (i.e the first and last neurons will be linked together).

featureInit - Arrays that will initialize the features sets of the network's neurons.

Throws:

NumberIsTooSmallException - if num < 2.

Method Detail

getNetwork

public Network getNetwork()

Retrieves the underlying network. A reference is returned (enabling, for example, the network to be trained). This also implies that calling methods that modify the Network topology may cause this class to become inconsistent.

Returns:

the network.

getSize

public int getSize()

Gets the number of neurons.

Returns:

the number of neurons.

getFeatures

public double[] getFeatures(int i)

Retrieves the features set from the neuron at location i in the map.

Parameters:

i - Neuron index.

Returns:

the features of the neuron at index i.

Throws:

OutOfRangeException - if i is out of range.

createLinks

private void createLinks()

Creates the neighbour relationships between neurons.

readObject

private void readObject(java.io.ObjectInputStream in)

Prevents proxy bypass.

Parameters:

in - Input stream.

writeReplace

private java.lang.Object writeReplace()

Custom serialization.

Returns:

the proxy instance that will be actually serialized.