org.aika

Class Model

java.lang.Object

org.aika.Model

public class Model
extends Object

The model consists of two layers. The first layer is the actual neural network consisting of neurons and synapses. The second layer is a pattern lattice containing a boolean logic representation of all the neurons. Whenever the synapse weights of a neuron are adjusted, then the underlying boolean logic representation of this neuron will be updated too.

The model supports parallel processing using a fixed number of threads.

Author:

Lukas Molzberger

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static interface	Model.AndNodeCheck
static interface	Model.StatisticFactory

Field Summary

Fields

Modifier and Type	Field and Description
Map<String,ActivationFunction>	activationFunctions
Map<Integer,Provider<? extends AbstractNode>>	activeProviders
Model.AndNodeCheck	andNodeCheck
AtomicInteger	currentId
int	defaultThreadId
AtomicInteger	docIdCounter
Document[]	docs
int[]	lastCleanup
Model.StatisticFactory	neuronStatisticFactory
Model.StatisticFactory	nodeStatisticFactory
int	numberOfThreads
WeakHashMap<Integer,WeakReference<Provider<? extends AbstractNode>>>	providers
SuspensionHook	suspensionHook
static AtomicLong	visitedCounter

Constructor Summary

Constructors

Constructor and Description
Model() Creates a model with a single thread.
Model(SuspensionHook sh, int numberOfThreads)

Method Summary

Modifier and Type	Method and Description
Document	createDocument(String txt)
Document	createDocument(String txt, int threadId)
Neuron	createNeuron()
Neuron	createNeuron(String label)
Neuron	createNeuron(String label, String outputText)
Model.AndNodeCheck	getAndNodeCheck()
Model.StatisticFactory	getNeuronStatisticFactory()
Model.StatisticFactory	getNodeStatisticFactory()
int	getOldestDocIdInProcessing()
SuspensionHook	getSuspensionHook()
Neuron	lookupNeuron(int id)
<P extends Provider<? extends Node>> P	lookupNodeProvider(int id)
void	register(Provider p)
void	registerActivationFunction(String key, ActivationFunction af)
void	removeProvider(Provider p)
void	setAndNodeCheck(Model.AndNodeCheck andNodeCheck)
void	setNeuronStatisticFactory(Model.StatisticFactory neuronStatisticFactory)
void	setNodeStatisticFactory(Model.StatisticFactory nodeStatisticFactory)
void	setSuspensionHook(SuspensionHook suspensionHook)
void	suspendAll(Provider.SuspensionMode sm) Suspend all neurons and logic nodes in memory.
void	suspendUnusedNodes(int docId, Provider.SuspensionMode sm) Suspend all neurons and logic nodes whose last used document id is lower/older than .
void	unregister(Provider p)

Methods inherited from class java.lang.Object

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

Field Detail

numberOfThreads

public int numberOfThreads

lastCleanup

public int[] lastCleanup

docs

public Document[] docs

suspensionHook

public SuspensionHook suspensionHook

nodeStatisticFactory

public Model.StatisticFactory nodeStatisticFactory

neuronStatisticFactory

public Model.StatisticFactory neuronStatisticFactory

andNodeCheck

public Model.AndNodeCheck andNodeCheck

docIdCounter

public AtomicInteger docIdCounter

currentId

public AtomicInteger currentId

providers

public WeakHashMap<Integer,WeakReference<Provider<? extends AbstractNode>>> providers

activeProviders

public Map<Integer,Provider<? extends AbstractNode>> activeProviders

activationFunctions

public Map<String,ActivationFunction> activationFunctions

defaultThreadId

public int defaultThreadId

visitedCounter

public static AtomicLong visitedCounter

Constructor Detail

Model

public Model()

Creates a model with a single thread.

Model

public Model(SuspensionHook sh,
             int numberOfThreads)

Method Detail

getSuspensionHook

public SuspensionHook getSuspensionHook()

setSuspensionHook

public void setSuspensionHook(SuspensionHook suspensionHook)

getNodeStatisticFactory

public Model.StatisticFactory getNodeStatisticFactory()

setNodeStatisticFactory

public void setNodeStatisticFactory(Model.StatisticFactory nodeStatisticFactory)

getNeuronStatisticFactory

public Model.StatisticFactory getNeuronStatisticFactory()

setNeuronStatisticFactory

public void setNeuronStatisticFactory(Model.StatisticFactory neuronStatisticFactory)

getAndNodeCheck

public Model.AndNodeCheck getAndNodeCheck()

setAndNodeCheck

public void setAndNodeCheck(Model.AndNodeCheck andNodeCheck)

registerActivationFunction

public void registerActivationFunction(String key,
                                       ActivationFunction af)

createNeuron

public Neuron createNeuron()

createNeuron

public Neuron createNeuron(String label)

createNeuron

public Neuron createNeuron(String label,
                           String outputText)

createDocument

public Document createDocument(String txt)

createDocument

public Document createDocument(String txt,
                               int threadId)

lookupNodeProvider

public <P extends Provider<? extends Node>> P lookupNodeProvider(int id)

lookupNeuron

public Neuron lookupNeuron(int id)

register

public void register(Provider p)

unregister

public void unregister(Provider p)

suspendUnusedNodes

public void suspendUnusedNodes(int docId,
                               Provider.SuspensionMode sm)

Suspend all neurons and logic nodes whose last used document id is lower/older than .

Parameters:

docId -

getOldestDocIdInProcessing

public int getOldestDocIdInProcessing()

suspendAll

public void suspendAll(Provider.SuspensionMode sm)

Suspend all neurons and logic nodes in memory.

removeProvider

public void removeProvider(Provider p)