Modifier and Type	Class and Description
public static enum	NeuronSquareMesh2D.HorizontalDirection Horizontal (along row) direction.
private static class	NeuronSquareMesh2D.SerializationProxy Serialization.
public static enum	NeuronSquareMesh2D.VerticalDirection Vertical (along column) direction.

Modifier and Type	Field and Description
private final long[][]	identifiers Mapping of the 2D coordinates (in the rectangular mesh) to the neuron identifiers (attributed by the `network` instance).
private final SquareNeighbourhood	neighbourhood Neighbourhood type.
private final Network	network Underlying network.
private final int	numberOfColumns Number of columns.
private final int	numberOfRows Number of rows.
private static final long	serialVersionUID Serial version ID
private final boolean	wrapColumns Wrap.
private final boolean	wrapRows Wrap.

Constructor Summary

Access	Constructor and Description
pack-priv	NeuronSquareMesh2D(boolean Whether to wrap the first dimension (i.e the first and last neurons will be linked together). wrapRowDim, boolean Whether to wrap the second dimension (i.e the first and last neurons will be linked together). wrapColDim, SquareNeighbourhood Neighbourhood type. neighbourhoodType, double[][][] Arrays that will initialize the features sets of the network's neurons. featuresList) Constructor with restricted access, solely used for deserialization.
public	NeuronSquareMesh2D(int Number of neurons in the first dimension. numRows, boolean Whether to wrap the first dimension (i.e the first and last neurons will be linked together). wrapRowDim, int Number of neurons in the second dimension. numCols, boolean Whether to wrap the second dimension (i.e the first and last neurons will be linked together). wrapColDim, SquareNeighbourhood Neighbourhood type. neighbourhoodType, FeatureInitializer[] Array of functions that will initialize the corresponding element of the features set of each newly created neuron. In particular, the size of this array defines the size of feature set. featureInit) Creates a two-dimensional network composed of square cells: Each neuron not located on the border of the mesh has four neurons linked to it.
private	NeuronSquareMesh2D(boolean Whether to wrap the first dimension (i.e the first and last neurons will be linked together). wrapRowDim, boolean Whether to wrap the second dimension (i.e the first and last neurons will be linked together). wrapColDim, SquareNeighbourhood Neighbourhood type. neighbourhoodType, Network Underlying network. net, long[][] Neuron identifiers. idGrid) Constructor with restricted access, solely used for making a `deep copy`.

Method Summary

Modifier and Type	Method and Description
public synchronized NeuronSquareMesh2D	Returns: a new instance with the same state as this instance. copy() Performs a deep copy of this instance.
private void	createLinks() Creates the neighbour relationships between neurons.
private int[]	Returns: an array of length 2 containing the indices of the requested location, or `null` if that location is not part of the map. getLocation(int Row index. row, int Column index. col, NeuronSquareMesh2D.HorizontalDirection Direction along the given `row` (i.e. an offset will be added to the given column index. alongRowDir, NeuronSquareMesh2D.VerticalDirection Direction along the given `col` (i.e. an offset will be added to the given row index. alongColDir) Computes the location of a neighbouring neuron.
public Network	Returns: the network. getNetwork() Retrieves the underlying network.
public Neuron	Returns: the neuron at `(i, j)`. getNeuron(int Row index. i, int Column index. j) Retrieves the neuron at location `(i, j)` in the map.
public Neuron	Returns: the neuron at the requested location, or `null` if the location is not on the map. getNeuron(int Row index. row, int Column index. col, NeuronSquareMesh2D.HorizontalDirection Direction along the given `row` (i.e. an offset will be added to the given column index. alongRowDir, NeuronSquareMesh2D.VerticalDirection Direction along the given `col` (i.e. an offset will be added to the given row index. alongColDir) Retrieves the neuron at `(location[0], location[1])` in the map.
public int	Returns: the number of column. getNumberOfColumns() Gets the number of neurons in each column of this map.
public int	Returns: the number of rows. getNumberOfRows() Gets the number of neurons in each row of this map.
public Iterator<Neuron>	iterator() Implements java.lang.Iterable.iterator. Returns an iterator over elements of type `T`.
private void	readObject(ObjectInputStream Input stream. in) Prevents proxy bypass.
private Object	Returns: the proxy instance that will be actually serialized. writeReplace() Custom serialization.

Inherited from java.lang.Object:: clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

Field Detail

identifiers	back to summary
private final long[][] identifiers Mapping of the 2D coordinates (in the rectangular mesh) to the neuron identifiers (attributed by the `network` instance).

neighbourhood	back to summary
private final SquareNeighbourhood neighbourhood Neighbourhood type.

network	back to summary
private final Network network Underlying network.

numberOfColumns	back to summary
private final int numberOfColumns Number of columns.

numberOfRows	back to summary
private final int numberOfRows Number of rows.

serialVersionUID	back to summary
private static final long serialVersionUID Serial version ID

wrapColumns	back to summary
private final boolean wrapColumns Wrap.

wrapRows	back to summary
private final boolean wrapRows Wrap.

Constructor Detail

NeuronSquareMesh2D back to summary

NeuronSquareMesh2D	back to summary
pack-priv NeuronSquareMesh2D(boolean wrapRowDim, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, double[][][] featuresList) Constructor with restricted access, solely used for deserialization. Parameters wrapRowDim:boolean Whether to wrap the first dimension (i.e the first and last neurons will be linked together). wrapColDim:boolean Whether to wrap the second dimension (i.e the first and last neurons will be linked together). neighbourhoodType:SquareNeighbourhood Neighbourhood type. featuresList:double[][][] Arrays that will initialize the features sets of the network's neurons. Exceptions NumberIsTooSmallException: if `numRows < 2` or `numCols < 2`.

pack-priv NeuronSquareMesh2D(boolean wrapRowDim, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, double[][][] featuresList)

Constructor with restricted access, solely used for deserialization.

Parameters

wrapRowDim:boolean: Whether to wrap the first dimension (i.e the first and last neurons will be linked together).
wrapColDim:boolean: Whether to wrap the second dimension (i.e the first and last neurons will be linked together).
neighbourhoodType:SquareNeighbourhood: Neighbourhood type.
featuresList:double[][][]: Arrays that will initialize the features sets of the network's neurons.

Exceptions

NumberIsTooSmallException:: if numRows < 2 or numCols < 2.

NeuronSquareMesh2D back to summary

NeuronSquareMesh2D	back to summary
public NeuronSquareMesh2D(int numRows, boolean wrapRowDim, int numCols, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, FeatureInitializer[] featureInit) Creates a two-dimensional network composed of square cells: Each neuron not located on the border of the mesh has four neurons linked to it. The links are bi-directional. The topology of the network can also be a cylinder (if one of the dimensions is wrapped) or a torus (if both dimensions are wrapped). Parameters numRows:int Number of neurons in the first dimension. wrapRowDim:boolean Whether to wrap the first dimension (i.e the first and last neurons will be linked together). numCols:int Number of neurons in the second dimension. wrapColDim:boolean Whether to wrap the second dimension (i.e the first and last neurons will be linked together). neighbourhoodType:SquareNeighbourhood Neighbourhood type. featureInit:FeatureInitializer[] Array of functions that will initialize the corresponding element of the features set of each newly created neuron. In particular, the size of this array defines the size of feature set. Exceptions NumberIsTooSmallException: if `numRows < 2` or `numCols < 2`.

public NeuronSquareMesh2D(int numRows, boolean wrapRowDim, int numCols, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, FeatureInitializer[] featureInit)

Creates a two-dimensional network composed of square cells: Each neuron not located on the border of the mesh has four neurons linked to it.
The links are bi-directional.
The topology of the network can also be a cylinder (if one of the dimensions is wrapped) or a torus (if both dimensions are wrapped).

Parameters

numRows:int: Number of neurons in the first dimension.
wrapRowDim:boolean: Whether to wrap the first dimension (i.e the first and last neurons will be linked together).
numCols:int: Number of neurons in the second dimension.
wrapColDim:boolean: Whether to wrap the second dimension (i.e the first and last neurons will be linked together).
neighbourhoodType:SquareNeighbourhood: Neighbourhood type.
featureInit:FeatureInitializer[]: Array of functions that will initialize the corresponding element of the features set of each newly created neuron. In particular, the size of this array defines the size of feature set.

Exceptions

NumberIsTooSmallException:: if numRows < 2 or numCols < 2.

NeuronSquareMesh2D back to summary

NeuronSquareMesh2D	back to summary
private NeuronSquareMesh2D(boolean wrapRowDim, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, Network net, long[][] idGrid) Constructor with restricted access, solely used for making a `deep copy`. Parameters wrapRowDim:boolean Whether to wrap the first dimension (i.e the first and last neurons will be linked together). wrapColDim:boolean Whether to wrap the second dimension (i.e the first and last neurons will be linked together). neighbourhoodType:SquareNeighbourhood Neighbourhood type. net:Network Underlying network. idGrid:long[][] Neuron identifiers.

private NeuronSquareMesh2D(boolean wrapRowDim, boolean wrapColDim, SquareNeighbourhood neighbourhoodType, Network net, long[][] idGrid)

Constructor with restricted access, solely used for making a deep copy.

Parameters

wrapRowDim:boolean: Whether to wrap the first dimension (i.e the first and last neurons will be linked together).
wrapColDim:boolean: Whether to wrap the second dimension (i.e the first and last neurons will be linked together).
neighbourhoodType:SquareNeighbourhood: Neighbourhood type.
net:Network: Underlying network.
idGrid:long[][]: Neuron identifiers.

Method Detail

copy	back to summary
public synchronized NeuronSquareMesh2D copy() Performs a deep copy of this instance. Upon return, the copied and original instances will be independent: Updating one will not affect the other. Returns:NeuronSquareMesh2D a new instance with the same state as this instance. Since 3.6

copy

back to summary

public synchronized NeuronSquareMesh2D copy()

Performs a deep copy of this instance. Upon return, the copied and original instances will be independent: Updating one will not affect the other.

Returns:NeuronSquareMesh2D: a new instance with the same state as this instance.
Since: 3.6

createLinks	back to summary
private void createLinks() Creates the neighbour relationships between neurons.

getLocation back to summary

getLocation	back to summary
private int[] getLocation(int row, int col, NeuronSquareMesh2D.HorizontalDirection alongRowDir, NeuronSquareMesh2D.VerticalDirection alongColDir) Computes the location of a neighbouring neuron. It will return `null` if the resulting location is not part of the map. Position `(0, 0)` is at the upper-left corner of the map. Parameters row:int Row index. col:int Column index. alongRowDir:NeuronSquareMesh2D.HorizontalDirection Direction along the given `row` (i.e. an offset will be added to the given column index. alongColDir:NeuronSquareMesh2D.VerticalDirection Direction along the given `col` (i.e. an offset will be added to the given row index. Returns:int[] an array of length 2 containing the indices of the requested location, or `null` if that location is not part of the map. See Also `getNeuron(int, int)`

private int[] getLocation(int row, int col, NeuronSquareMesh2D.HorizontalDirection alongRowDir, NeuronSquareMesh2D.VerticalDirection alongColDir)

Computes the location of a neighbouring neuron. It will return null if the resulting location is not part of the map. Position (0, 0) is at the upper-left corner of the map.

Parameters

row:int: Row index.
col:int: Column index.
alongRowDir:NeuronSquareMesh2D.HorizontalDirection: Direction along the given row (i.e. an offset will be added to the given column index.
alongColDir:NeuronSquareMesh2D.VerticalDirection: Direction along the given col (i.e. an offset will be added to the given row index.

Returns:int[]

an array of length 2 containing the indices of the requested location, or null if that location is not part of the map.

See Also

getNeuron(int, int)

getNetwork back to summary

getNetwork	back to summary
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:Network the network.

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:Network: the network.

getNeuron back to summary

getNeuron	back to summary
public Neuron getNeuron(int i, int j) Retrieves the neuron at location `(i, j)` in the map. The neuron at position `(0, 0)` is located at the upper-left corner of the map. Parameters i:int Row index. j:int Column index. Returns:Neuron the neuron at `(i, j)`. Exceptions OutOfRangeException: if `i` or `j` is out of range. See Also `getNeuron(int, int, HorizontalDirection, VerticalDirection)`

public Neuron getNeuron(int i, int j)

Retrieves the neuron at location (i, j) in the map. The neuron at position (0, 0) is located at the upper-left corner of the map.

Parameters

i:int: Row index.
j:int: Column index.

Returns:Neuron

the neuron at (i, j).

Exceptions

OutOfRangeException:: if i or j is out of range.

getNeuron back to summary

getNeuron	back to summary
public Neuron getNeuron(int row, int col, NeuronSquareMesh2D.HorizontalDirection alongRowDir, NeuronSquareMesh2D.VerticalDirection alongColDir) Retrieves the neuron at `(location[0], location[1])` in the map. The neuron at position `(0, 0)` is located at the upper-left corner of the map. Parameters row:int Row index. col:int Column index. alongRowDir:NeuronSquareMesh2D.HorizontalDirection Direction along the given `row` (i.e. an offset will be added to the given column index. alongColDir:NeuronSquareMesh2D.VerticalDirection Direction along the given `col` (i.e. an offset will be added to the given row index. Returns:Neuron the neuron at the requested location, or `null` if the location is not on the map. See Also `getNeuron(int, int)`

public Neuron getNeuron(int row, int col, NeuronSquareMesh2D.HorizontalDirection alongRowDir, NeuronSquareMesh2D.VerticalDirection alongColDir)

Retrieves the neuron at (location[0], location[1]) in the map. The neuron at position (0, 0) is located at the upper-left corner of the map.

Parameters

row:int: Row index.
col:int: Column index.
alongRowDir:NeuronSquareMesh2D.HorizontalDirection: Direction along the given row (i.e. an offset will be added to the given column index.
alongColDir:NeuronSquareMesh2D.VerticalDirection: Direction along the given col (i.e. an offset will be added to the given row index.

Returns:Neuron

the neuron at the requested location, or null if the location is not on the map.

See Also

getNeuron(int, int)

getNumberOfColumns	back to summary
public int getNumberOfColumns() Gets the number of neurons in each column of this map. Returns:int the number of column.

getNumberOfColumns

back to summary

public int getNumberOfColumns()

Gets the number of neurons in each column of this map.

Returns:int: the number of column.

getNumberOfRows	back to summary
public int getNumberOfRows() Gets the number of neurons in each row of this map. Returns:int the number of rows.

getNumberOfRows

back to summary

public int getNumberOfRows()

Gets the number of neurons in each row of this map.

Returns:int: the number of rows.

iterator back to summary

iterator	back to summary
public Iterator<Neuron> iterator() Implements java.lang.Iterable.iterator. Doc from java.lang.Iterable.iterator. Returns an iterator over elements of type `T`. Returns:Iterator<Neuron> an Iterator. Since 3.6

public Iterator<Neuron> iterator()

Implements java.lang.Iterable.iterator.

Doc from java.lang.Iterable.iterator.

Returns an iterator over elements of type T.

Returns:Iterator<Neuron>: an Iterator.
Since: 3.6

readObject	back to summary
private void readObject(ObjectInputStream in) Prevents proxy bypass. Parameters in:ObjectInputStream Input stream.

readObject

back to summary

private void readObject(ObjectInputStream in)

Prevents proxy bypass.

Parameters

in:ObjectInputStream: Input stream.

writeReplace	back to summary
private Object writeReplace() Custom serialization. Returns:Object the proxy instance that will be actually serialized.

writeReplace

back to summary

private Object writeReplace()

Custom serialization.

Returns:Object: the proxy instance that will be actually serialized.

org.apache.commons.math3.ml.neuralnet.twod back to summary

public final Enum NeuronSquareMesh2D.HorizontalDirection

Class Inheritance

extends Enum<NeuronSquareMesh2D.HorizontalDirection>

java.lang.Object
java.lang.Enum
org.apache.commons.math3.ml.neuralnet.twod.NeuronSquareMesh2D.HorizontalDirection

Horizontal (along row) direction.

Since: 3.6

Field Summary

Modifier and Type	Field and Description
public static final NeuronSquareMesh2D.HorizontalDirection	CENTER Current column.
public static final NeuronSquareMesh2D.HorizontalDirection	LEFT Column at the left of the current column.
public static final NeuronSquareMesh2D.HorizontalDirection	RIGHT Column at the right of the current column.

Constructor Summary

Access	Constructor and Description
private	HorizontalDirection()

Method Summary

Modifier and Type	Method and Description
public static NeuronSquareMesh2D.HorizontalDirection	valueOf(String name)
public static NeuronSquareMesh2D.HorizontalDirection[]	values()

Inherited from java.lang.Enum:: clone compareTo describeConstable equals finalize getDeclaringClass hashCode name ordinal toString valueOf

Field Detail

CENTER	back to summary
public static final NeuronSquareMesh2D.HorizontalDirection CENTER Current column.

LEFT	back to summary
public static final NeuronSquareMesh2D.HorizontalDirection LEFT Column at the left of the current column.

RIGHT	back to summary
public static final NeuronSquareMesh2D.HorizontalDirection RIGHT Column at the right of the current column.

Constructor Detail

HorizontalDirection	back to summary
private HorizontalDirection()

Method Detail

valueOf	back to summary
public static NeuronSquareMesh2D.HorizontalDirection valueOf(String name)

values	back to summary
public static NeuronSquareMesh2D.HorizontalDirection[] values()

org.apache.commons.math3.ml.neuralnet.twod back to summary

private Class NeuronSquareMesh2D.SerializationProxy

Class Inheritance

extends Object
implements Serializable

java.lang.Object
org.apache.commons.math3.ml.neuralnet.twod.NeuronSquareMesh2D.SerializationProxy

All Implemented Interfaces

java.io.Serializable

Serialization.

Field Summary

Modifier and Type	Field and Description
private final double[][][]	featuresList Neurons' features.
private final SquareNeighbourhood	neighbourhood Neighbourhood type.
private static final long	serialVersionUID Serializable.
private final boolean	wrapColumns Wrap.
private final boolean	wrapRows Wrap.

Constructor Summary

Access	Constructor and Description
pack-priv	SerializationProxy(boolean Whether the row dimension is wrapped. wrapRows, boolean Whether the column dimension is wrapped. wrapColumns, SquareNeighbourhood Neighbourhood type. neighbourhood, double[][][] List of neurons features. `neuronList`. featuresList)

Method Summary

Modifier and Type	Method and Description
private Object	Returns: the `Neuron` for which this instance is the proxy. readResolve() Custom serialization.

Inherited from java.lang.Object:: clone equals finalize getClass hashCode notify notifyAll toString wait wait wait

Field Detail

featuresList	back to summary
private final double[][][] featuresList Neurons' features.

neighbourhood	back to summary
private final SquareNeighbourhood neighbourhood Neighbourhood type.

serialVersionUID	back to summary
private static final long serialVersionUID Serializable.

wrapColumns	back to summary
private final boolean wrapColumns Wrap.

wrapRows	back to summary
private final boolean wrapRows Wrap.

Constructor Detail

SerializationProxy	back to summary
pack-priv SerializationProxy(boolean wrapRows, boolean wrapColumns, SquareNeighbourhood neighbourhood, double[][][] featuresList) Parameters wrapRows:boolean Whether the row dimension is wrapped. wrapColumns:boolean Whether the column dimension is wrapped. neighbourhood:SquareNeighbourhood Neighbourhood type. featuresList:double[][][] List of neurons features. `neuronList`.

Method Detail

readResolve back to summary

readResolve	back to summary
private Object readResolve() Custom serialization. Returns:Object the `Neuron` for which this instance is the proxy.

private Object readResolve()

Custom serialization.

Returns:Object: the Neuron for which this instance is the proxy.

org.apache.commons.math3.ml.neuralnet.twod back to summary

public final Enum NeuronSquareMesh2D.VerticalDirection

Class Inheritance

extends Enum<NeuronSquareMesh2D.VerticalDirection>

java.lang.Object
java.lang.Enum
org.apache.commons.math3.ml.neuralnet.twod.NeuronSquareMesh2D.VerticalDirection

Vertical (along column) direction.

Since: 3.6

Field Summary

Modifier and Type	Field and Description
public static final NeuronSquareMesh2D.VerticalDirection	CENTER Current row.
public static final NeuronSquareMesh2D.VerticalDirection	DOWN Row below the current row.
public static final NeuronSquareMesh2D.VerticalDirection	UP Row above the current row.

Constructor Summary

Access	Constructor and Description
private	VerticalDirection()

Method Summary

Modifier and Type	Method and Description
public static NeuronSquareMesh2D.VerticalDirection	valueOf(String name)
public static NeuronSquareMesh2D.VerticalDirection[]	values()

Inherited from java.lang.Enum:: clone compareTo describeConstable equals finalize getDeclaringClass hashCode name ordinal toString valueOf

Field Detail

CENTER	back to summary
public static final NeuronSquareMesh2D.VerticalDirection CENTER Current row.

DOWN	back to summary
public static final NeuronSquareMesh2D.VerticalDirection DOWN Row below the current row.

UP	back to summary
public static final NeuronSquareMesh2D.VerticalDirection UP Row above the current row.

Constructor Detail

VerticalDirection	back to summary
private VerticalDirection()

Method Detail

valueOf	back to summary
public static NeuronSquareMesh2D.VerticalDirection valueOf(String name)

values	back to summary
public static NeuronSquareMesh2D.VerticalDirection[] values()

public Class NeuronSquareMesh2D

Nested and Inner Type Summary

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail

public final Enum NeuronSquareMesh2D.HorizontalDirection

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail

private Class NeuronSquareMesh2D.SerializationProxy

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail

public final Enum NeuronSquareMesh2D.VerticalDirection

Field Summary

Constructor Summary

Method Summary

Field Detail

Constructor Detail

Method Detail