network.aika.neuron

Class Neuron

java.lang.Object

network.aika.Provider<INeuron>

network.aika.neuron.Neuron

All Implemented Interfaces:

Comparable<Provider<?>>

public class Neuron
extends Provider<INeuron>

The Neuron class is a proxy implementation for the real neuron implementation in the class INeuron. Aika uses the provider pattern to store and reload rarely used neurons or logic nodes.

Author:

Lukas Molzberger

Nested Class Summary

Nested classes/interfaces inherited from class network.aika.Provider

Provider.SuspensionMode

Field Summary

Fields

Modifier and Type	Field and Description
NavigableMap<Synapse,Synapse>	inMemoryInputSynapses
NavigableMap<Synapse,Synapse>	inMemoryOutputSynapses
NavigableMap<Integer,Synapse>	inputSynapsesById
ReadWriteLock	lock
static Neuron	MAX_NEURON
static Neuron	MIN_NEURON

Fields inherited from class network.aika.Provider

id, model

Constructor Summary

Constructors

Constructor and Description
Neuron(Model m, INeuron n)
Neuron(Model m, int id)

Method Summary

Modifier and Type	Method and Description
void	addInMemoryInputSynapse(Synapse s)
void	addInMemoryOutputSynapse(Synapse s)
Activation	addInput(Document doc, Activation.Builder inputAct) Propagate an input activation into the network.
Activation	addInput(Document doc, int begin, int end) Propagate an input activation into the network.
Activation	addInput(Document doc, Range r) Propagate an input activation into the network.
void	addSynapse(Document doc, Synapse.Builder input)
void	addSynapse(Synapse.Builder input)
Activation	getActivation(Document doc, Range r, boolean onlyFinal)
Collection<Activation>	getActivations(Document doc, boolean onlyFinal) getFinalActivations is a convenience method to retrieve all activations of the given neuron that are part of the final interpretation.
String	getLabel()
Synapse	getSynapseById(int synapseId)
boolean	init(Document doc, double bias, ActivationFunction activationFunction, INeuron.Type type, INeuron.LogicType logicType, List<Synapse.Builder> inputs)
static Neuron	init(Document doc, Neuron n, double bias, ActivationFunction activationFunction, INeuron.Type type, INeuron.LogicType logicType, List<Synapse.Builder> inputs) Initializes a neuron with the given bias.
static Neuron	init(Document doc, Neuron n, double bias, ActivationFunction activationFunction, INeuron.Type type, INeuron.LogicType logicType, Synapse.Builder... inputs) Creates a neuron with the given bias.
static Neuron	init(Document doc, Neuron n, double bias, INeuron.Type type, INeuron.LogicType logicType, Synapse.Builder... inputs) Creates a neuron with the given bias.
boolean	init(double bias, ActivationFunction activationFunction, INeuron.Type type, INeuron.LogicType logicType, List<Synapse.Builder> inputs) Initializes a neuron with the given bias.
static Neuron	init(Neuron n, double bias, ActivationFunction activationFunction, INeuron.Type type, INeuron.LogicType logicType, List<Synapse.Builder> inputs) Initializes a neuron with the given bias.
static Neuron	init(Neuron n, double bias, ActivationFunction activationFunction, INeuron.Type type, INeuron.LogicType logicType, Synapse.Builder... inputs) Creates a neuron with the given bias.
static Neuron	init(Neuron n, double bias, INeuron.Type type, INeuron.LogicType logicType, List<Synapse.Builder> inputs) Creates a neuron with the given bias.
static Neuron	init(Neuron n, double bias, INeuron.Type type, INeuron.LogicType logicType, Synapse.Builder... inputs) Creates a neuron with the given bias.
static void	registerPassiveInputNeuron(Neuron n, PassiveInputFunction f)
void	removeInMemoryInputSynapse(Synapse s)
void	removeInMemoryOutputSynapse(Synapse s)
String	toString()

Methods inherited from class network.aika.Provider

compareTo, equals, get, get, get, getIfNotSuspended, hashCode, isSuspended, save, suspend

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

MIN_NEURON

public static final Neuron MIN_NEURON

MAX_NEURON

public static final Neuron MAX_NEURON

lock

public ReadWriteLock lock

inputSynapsesById

public NavigableMap<Integer,Synapse> inputSynapsesById

inMemoryInputSynapses

public NavigableMap<Synapse,Synapse> inMemoryInputSynapses

inMemoryOutputSynapses

public NavigableMap<Synapse,Synapse> inMemoryOutputSynapses

Constructor Detail

Neuron

public Neuron(Model m,
              int id)

Neuron

public Neuron(Model m,
              INeuron n)

Method Detail

getLabel

public String getLabel()

addInput

public Activation addInput(Document doc,
                           int begin,
                           int end)

Propagate an input activation into the network.

Parameters:

doc - The current document

begin - The range begin

end - The range end

addInput

public Activation addInput(Document doc,
                           Range r)

Propagate an input activation into the network.

Parameters:

doc - The current document

r - The range

addInput

public Activation addInput(Document doc,
                           Activation.Builder inputAct)

Propagate an input activation into the network.

Parameters:

doc - The current document

inputAct -

init

public static Neuron init(Neuron n,
                          double bias,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          Synapse.Builder... inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public static Neuron init(Document doc,
                          Neuron n,
                          double bias,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          Synapse.Builder... inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public static Neuron init(Neuron n,
                          double bias,
                          ActivationFunction activationFunction,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          Synapse.Builder... inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public static Neuron init(Document doc,
                          Neuron n,
                          double bias,
                          ActivationFunction activationFunction,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          Synapse.Builder... inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public static Neuron init(Neuron n,
                          double bias,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          List<Synapse.Builder> inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public static Neuron init(Neuron n,
                          double bias,
                          ActivationFunction activationFunction,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          List<Synapse.Builder> inputs)

Initializes a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public static Neuron init(Document doc,
                          Neuron n,
                          double bias,
                          ActivationFunction activationFunction,
                          INeuron.Type type,
                          INeuron.LogicType logicType,
                          List<Synapse.Builder> inputs)

Initializes a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

init

public boolean init(double bias,
                    ActivationFunction activationFunction,
                    INeuron.Type type,
                    INeuron.LogicType logicType,
                    List<Synapse.Builder> inputs)

Initializes a neuron with the given bias.

Parameters:

bias -

inputs -

Returns:

init

public boolean init(Document doc,
                    double bias,
                    ActivationFunction activationFunction,
                    INeuron.Type type,
                    INeuron.LogicType logicType,
                    List<Synapse.Builder> inputs)

addSynapse

public void addSynapse(Synapse.Builder input)

addSynapse

public void addSynapse(Document doc,
                       Synapse.Builder input)

registerPassiveInputNeuron

public static void registerPassiveInputNeuron(Neuron n,
                                              PassiveInputFunction f)

getSynapseById

public Synapse getSynapseById(int synapseId)

getActivations

public Collection<Activation> getActivations(Document doc,
                                             boolean onlyFinal)

getFinalActivations is a convenience method to retrieve all activations of the given neuron that are part of the final interpretation. Before calling this method, the doc.process() needs to be called first. getFinalActivations requires that the doc.process() method has been called first.

Parameters:

doc - The current document

Returns:

A collection with all final activations of this neuron.

getActivation

public Activation getActivation(Document doc,
                                Range r,
                                boolean onlyFinal)

addInMemoryInputSynapse

public void addInMemoryInputSynapse(Synapse s)

removeInMemoryInputSynapse

public void removeInMemoryInputSynapse(Synapse s)

addInMemoryOutputSynapse

public void addInMemoryOutputSynapse(Synapse s)

removeInMemoryOutputSynapse

public void removeInMemoryOutputSynapse(Synapse s)

toString

public String toString()

Overrides:

toString in class Provider<INeuron>