org.aika.lattice

Class OrNode

java.lang.Object

org.aika.AbstractNode<Provider<T>>

org.aika.lattice.Node<OrNode,Activation>

org.aika.lattice.OrNode

All Implemented Interfaces:

Comparable<Node>, Writable

public class OrNode
extends Node<OrNode,Activation>

While several neurons might share a the same input-node or and-node, there is always a always a one-to-one relation between or-nodes and neurons. The only exceptions are the input neurons which have a one-to-one relation with the input-node. The or-nodes form a disjunction of one or more input-nodes or and-nodes.

Author:

Lukas Molzberger

Nested Class Summary

Nested classes/interfaces inherited from class org.aika.lattice.Node

Node.RidVisited, Node.ThreadState<T extends Node,A extends NodeActivation<T>>

Field Summary

Fields

Modifier and Type	Field and Description
TreeMap<Integer,TreeSet<Provider<Node>>>	allParents
Neuron	neuron
TreeMap<Integer,TreeSet<Provider<Node>>>	parents
Node	requiredNode

Fields inherited from class org.aika.lattice.Node

BEGIN_COMP, END_COMP, endRequired, frequency, frequencyHasChanged, instanceSum, isDiscovered, isQueued, level, lock, MAX_NODE, MAX_RID, MIN_NODE, nOffset, nullHypFreq, numberOfNeuronRefs, oldNullHypFreq, queueId, RID_COMP, ridRequired, sizeSum, threads, visitedCounter

Fields inherited from class org.aika.AbstractNode

lastUsedDocumentId, provider

Constructor Summary

Constructors

Constructor and Description
OrNode()
OrNode(Model m)

Method Summary

Modifier and Type	Method and Description
void	addActivation(Document doc, Integer ridOffset, NodeActivation inputAct)
void	addInput(Integer ridOffset, int threadId, Node in, boolean all)
void	apply(Document doc, Activation act, InterprNode conflict)
void	changeNumberOfNeuronRefs(int threadId, long v, int d)
void	cleanup(Model m)
void	computeNullHyp(Model m)
double	computeSynapseWeightSum(Integer offset, INeuron n)
protected Activation	createActivation(Document doc, NodeActivation.Key ak, boolean isTrainingAct)
void	deleteActivation(Document doc, Activation act)
void	discover(Document doc, NodeActivation act, TrainConfig trainConfig)
String	getNeuronLabel()
boolean	hasParent(Integer ridOffset, Node in, boolean all)
boolean	isAllowedOption(int threadId, InterprNode n, NodeActivation act, long v)
boolean	isExpandable()
String	logicToString()
InterprNode	lookupOrOption(Document doc, Range r, boolean create)
static void	processCandidate(Document doc, Node<?,? extends NodeActivation<?>> parentNode, NodeActivation inputAct, boolean train)
void	propagateAddedActivation(Document doc, Activation act, InterprNode removedConflict) Propagate an activation to the next node or the next neuron that is depending on the current node.
void	propagateRemovedActivation(Document doc, NodeActivation act)
void	readFields(DataInput in, Model m) Deserialize the fields of this object from in.
void	register(Activation act, Document doc)
void	removeActivation(Document doc, Integer ridOffset, NodeActivation<?> inputAct)
void	removeInput(Integer ridOffset, int threadId, Node in, boolean all)
void	removeParents(int threadId, boolean all)
void	unregister(Activation act, Document doc)
void	write(DataOutput out) Serialize the fields of this object to out.

Methods inherited from class org.aika.lattice.Node

addActivationAndPropagate, clearActivations, clearActivations, clearActivations, compareTo, count, getActivations, getFirstActivation, getThreadState, isCovered, isPublic, isRequired, processChanges, readNode, removeActivationAndPropagate, toString, weightsToString

Methods inherited from class org.aika.AbstractNode

reactivate, read, suspend

Methods inherited from class java.lang.Object

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

Field Detail

parents

public TreeMap<Integer,TreeSet<Provider<Node>>> parents

allParents

public TreeMap<Integer,TreeSet<Provider<Node>>> allParents

neuron

public Neuron neuron

requiredNode

public Node requiredNode

Constructor Detail

OrNode

public OrNode()

OrNode

public OrNode(Model m)

Method Detail

computeNullHyp

public void computeNullHyp(Model m)

Specified by:

computeNullHyp in class Node<OrNode,Activation>

isExpandable

public boolean isExpandable()

Specified by:

isExpandable in class Node<OrNode,Activation>

isAllowedOption

public boolean isAllowedOption(int threadId,
                               InterprNode n,
                               NodeActivation act,
                               long v)

Specified by:

isAllowedOption in class Node<OrNode,Activation>

createActivation

protected Activation createActivation(Document doc,
                                      NodeActivation.Key ak,
                                      boolean isTrainingAct)

deleteActivation

public void deleteActivation(Document doc,
                             Activation act)

addActivation

public void addActivation(Document doc,
                          Integer ridOffset,
                          NodeActivation inputAct)

removeActivation

public void removeActivation(Document doc,
                             Integer ridOffset,
                             NodeActivation<?> inputAct)

propagateAddedActivation

public void propagateAddedActivation(Document doc,
                                     Activation act,
                                     InterprNode removedConflict)

Description copied from class: Node

Propagate an activation to the next node or the next neuron that is depending on the current node.

Specified by:

propagateAddedActivation in class Node<OrNode,Activation>

propagateRemovedActivation

public void propagateRemovedActivation(Document doc,
                                       NodeActivation act)

Specified by:

propagateRemovedActivation in class Node<OrNode,Activation>

computeSynapseWeightSum

public double computeSynapseWeightSum(Integer offset,
                                      INeuron n)

Specified by:

computeSynapseWeightSum in class Node<OrNode,Activation>

cleanup

public void cleanup(Model m)

Specified by:

cleanup in class Node<OrNode,Activation>

apply

public void apply(Document doc,
                  Activation act,
                  InterprNode conflict)

discover

public void discover(Document doc,
                     NodeActivation act,
                     TrainConfig trainConfig)

Specified by:

discover in class Node<OrNode,Activation>

processCandidate

public static void processCandidate(Document doc,
                                    Node<?,? extends NodeActivation<?>> parentNode,
                                    NodeActivation inputAct,
                                    boolean train)

lookupOrOption

public InterprNode lookupOrOption(Document doc,
                                  Range r,
                                  boolean create)

addInput

public void addInput(Integer ridOffset,
                     int threadId,
                     Node in,
                     boolean all)

hasParent

public boolean hasParent(Integer ridOffset,
                         Node in,
                         boolean all)

removeInput

public void removeInput(Integer ridOffset,
                        int threadId,
                        Node in,
                        boolean all)

removeParents

public void removeParents(int threadId,
                          boolean all)

register

public void register(Activation act,
                     Document doc)

Overrides:

register in class Node<OrNode,Activation>

unregister

public void unregister(Activation act,
                       Document doc)

Overrides:

unregister in class Node<OrNode,Activation>

changeNumberOfNeuronRefs

public void changeNumberOfNeuronRefs(int threadId,
                                     long v,
                                     int d)

Specified by:

changeNumberOfNeuronRefs in class Node<OrNode,Activation>

logicToString

public String logicToString()

Specified by:

logicToString in class Node<OrNode,Activation>

write

public void write(DataOutput out)
           throws IOException

Description copied from interface: Writable

Serialize the fields of this object to out.

Specified by:

write in interface Writable

Overrides:

write in class Node<OrNode,Activation>

Parameters:

out - DataOuput to serialize this object into.

Throws:

IOException

readFields

public void readFields(DataInput in,
                       Model m)
                throws IOException

Description copied from interface: Writable

Deserialize the fields of this object from in.

For efficiency, implementations should attempt to re-use storage in the existing object where possible.

Specified by:

readFields in interface Writable

Overrides:

readFields in class Node<OrNode,Activation>

Parameters:

in - DataInput to deseriablize this object from.

Throws:

IOException

getNeuronLabel

public String getNeuronLabel()

Overrides:

getNeuronLabel in class Node<OrNode,Activation>