Package org.apache.commons.math4.neuralnet

Class Network

java.lang.Object

org.apache.commons.math4.neuralnet.Network

All Implemented Interfaces:

Iterable<Neuron>

public class Network
extends Object
implements Iterable<Neuron>

Neural network, composed of Neuron instances and the links between them. Although updating a neuron's state is thread-safe, modifying the network's topology (adding or removing links) is not.

Since:

3.3

Constructor Summary

Constructors

Constructor	Description
Network(long firstId, int featureSize)

Method Summary

Modifier and Type	Method	Description
void	addLink(Neuron a, Neuron b)	Adds a link from neuron a to neuron b.
Network	copy()	Performs a deep copy of this instance.
long	createNeuron(double[] features)	Creates a neuron and assigns it a unique identifier.
void	deleteLink(Neuron a, Neuron b)	Deletes the link between neurons a and b.
void	deleteNeuron(Neuron neuron)	Deletes a neuron.
static Network	from(int featureSize, long[] idList, double[][] featureList, long[][] neighbourIdList)	Builds a network from a list of neurons and their neighbours.
int	getFeaturesSize()	Gets the size of the neurons' features set.
Collection<Neuron>	getNeighbours(Iterable<Neuron> neurons)	Retrieves the neurons in the neighbourhood of any neuron in the neurons list.
Collection<Neuron>	getNeighbours(Iterable<Neuron> neurons, Iterable<Neuron> exclude)	Retrieves the neurons in the neighbourhood of any neuron in the neurons list.
Collection<Neuron>	getNeighbours(Neuron neuron)	Retrieves the neighbours of the given neuron.
Collection<Neuron>	getNeighbours(Neuron neuron, Iterable<Neuron> exclude)	Retrieves the neighbours of the given neuron.
Neuron	getNeuron(long id)	Retrieves the neuron with the given (unique) id.
Collection<Neuron>	getNeurons()
Iterator<Neuron>	iterator()

Methods inherited from class java.lang.Object

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

Methods inherited from interface java.lang.Iterable

forEach, spliterator

Constructor Detail

Network

public Network(long firstId,
               int featureSize)

Parameters:

firstId - Identifier of the first neuron that will be added to this network.

featureSize - Size of the neuron's features.

Method Detail

from

public static Network from(int featureSize,
                           long[] idList,
                           double[][] featureList,
                           long[][] neighbourIdList)

Builds a network from a list of neurons and their neighbours.

Parameters:

featureSize - Number of features.

idList - List of neuron identifiers.

featureList - List of neuron features.

neighbourIdList - Links associated to each of the neurons in idList.

Returns:

a new instance.

Throws:

IllegalArgumentException - if an inconsistency is detected.

copy

public Network 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:

a new instance with the same state as this instance.

Since:

3.6

iterator

public Iterator<Neuron> iterator()

Specified by:

iterator in interface Iterable<Neuron>

getNeurons

public Collection<Neuron> getNeurons()

Returns:

a shallow copy of the network's neurons.

createNeuron

public long createNeuron(double[] features)

Creates a neuron and assigns it a unique identifier.

Parameters:

features - Initial values for the neuron's features.

Returns:

the neuron's identifier.

Throws:

IllegalArgumentException - if the length of features is different from the expected size (as set by the constructor).

deleteNeuron

public void deleteNeuron(Neuron neuron)

Deletes a neuron. Links from all neighbours to the removed neuron will also be deleted.

Parameters:

neuron - Neuron to be removed from this network.

Throws:

NoSuchElementException - if n does not belong to this network.

getFeaturesSize

public int getFeaturesSize()

Gets the size of the neurons' features set.

Returns:

the size of the features set.

addLink

public void addLink(Neuron a,
                    Neuron b)

Adds a link from neuron a to neuron b. Note: the link is not bi-directional; if a bi-directional link is required, an additional call must be made with a and b exchanged in the argument list.

Parameters:

a - Neuron.

b - Neuron.

Throws:

NoSuchElementException - if the neurons do not exist in the network.

deleteLink

public void deleteLink(Neuron a,
                       Neuron b)

Deletes the link between neurons a and b.

Parameters:

a - Neuron.

b - Neuron.

Throws:

NoSuchElementException - if the neurons do not exist in the network.

getNeuron

public Neuron getNeuron(long id)

Retrieves the neuron with the given (unique) id.

Parameters:

id - Identifier.

Returns:

the neuron associated with the given id.

Throws:

NoSuchElementException - if the neuron does not exist in the network.

getNeighbours

public Collection<Neuron> getNeighbours(Iterable<Neuron> neurons)

Retrieves the neurons in the neighbourhood of any neuron in the neurons list.

Parameters:

neurons - Neurons for which to retrieve the neighbours.

Returns:

the list of neighbours.

See Also:

getNeighbours(Iterable,Iterable)

getNeighbours

public Collection<Neuron> getNeighbours(Iterable<Neuron> neurons,
                                        Iterable<Neuron> exclude)

Retrieves the neurons in the neighbourhood of any neuron in the neurons list. The exclude list allows to retrieve the "concentric" neighbourhoods by removing the neurons that belong to the inner "circles".

Parameters:

neurons - Neurons for which to retrieve the neighbours.

exclude - Neurons to exclude from the returned list. Can be null.

Returns:

the list of neighbours.

getNeighbours

public Collection<Neuron> getNeighbours(Neuron neuron)

Retrieves the neighbours of the given neuron.

Parameters:

neuron - Neuron for which to retrieve the neighbours.

Returns:

the list of neighbours.

See Also:

getNeighbours(Neuron,Iterable)

getNeighbours

public Collection<Neuron> getNeighbours(Neuron neuron,
                                        Iterable<Neuron> exclude)

Retrieves the neighbours of the given neuron.

Parameters:

neuron - Neuron for which to retrieve the neighbours.

exclude - Neurons to exclude from the returned list. Can be null.

Returns:

the list of neighbours.