org.aika.network.neuron.simple.lattice

Class InputNode

java.lang.Object

org.aika.network.neuron.Node

org.aika.network.neuron.simple.lattice.LatticeNode

org.aika.network.neuron.simple.lattice.InputNode

All Implemented Interfaces:

Comparable<Node>, Input

Direct Known Subclasses:

NegativeInputNode, PositiveInputNode

public abstract class InputNode
extends LatticeNode
implements Input

Author:

Lukas Molzberger

Nested Class Summary

Nested classes/interfaces inherited from class org.aika.network.neuron.simple.lattice.LatticeNode

LatticeNode.RSKey

Nested classes/interfaces inherited from class org.aika.network.neuron.Node

Node.Queue

Nested classes/interfaces inherited from interface org.aika.network.neuron.Input

Input.InputKey

Field Summary

Fields

Modifier and Type	Field and Description
Neuron	inputNeuron
Integer	rid

Fields inherited from class org.aika.network.neuron.simple.lattice.LatticeNode

andChildren, andChildrenWithinDocument, orChildren, visitedAllowedOption, visitedCollectPublicNodes, visitedPropagateSignificance

Fields inherited from class org.aika.network.neuron.Node

activations, added, countingMode, currentNodeId, frequency, frequencyHasChanged, id, isBlocked, isPredefined, isQueued, isRemoved, isRemovedId, isRemovedIdCounter, level, MAX_NODE, MIN_NODE, minFrequency, n, neuron, removed, visitedCounter, weight

Constructor Summary

Constructors

Constructor and Description
InputNode(Model m, Integer rid)

Method Summary

Modifier and Type	Method and Description
static InputNode	add(Model m, Integer rid, Neuron input, boolean isNeg)
void	addActivation(Iteration t, Activation inputAct, Range addedRange)
protected void	collectNodeAndRefinements(AndNode.Refinement newRef, Set<AndNode.Refinement> inputs)
double	computeSynapseWeightSum(Neuron n)
void	deleteActivation(Iteration t, Activation act)
void	expandToNextLevel(Iteration t, Activation act, Range addedRange, Option removedConflict, boolean train)
abstract int	getSign()
void	initActivation(Iteration t, Activation act)
boolean	isAllowedOption(Option n, Activation act, long v)
String	logicToString()
void	removeActivation(Iteration t, Activation inputAct, Range removedRange)

Methods inherited from class org.aika.network.neuron.simple.lattice.LatticeNode

addNeuron, collectPublicNodes, computeAndParents, computePredefinedAndNodes, computePredefinedInputNodes, computePredefinedSecondLevelAndNodes, getAndChildPatterns, isPublic, propagateAddedActivation, propagateRemovedActivation, remove, removeFromNextLevel, train

Methods inherited from class org.aika.network.neuron.Node

addActivationAndPropagate, addActivationInternal, cleanup, clearActivations, compare, compareTo, computeForwardWeight, containsNegative, countActivation, getActivations, getFirstActivation, getNodeWeight, getSelectedActivations, isFrequentOrPredefined, isFrequentOrPredefined, isNegative, processAddedActivations, processRemovedActivations, removeActivationAndPropagate, removeActivationInternal, retrieveInitialOption, toSimpleString, toString

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.aika.network.neuron.Input

remove

Field Detail

rid

public Integer rid

inputNeuron

public Neuron inputNeuron

Constructor Detail

InputNode

public InputNode(Model m,
                 Integer rid)

Method Detail

add

public static InputNode add(Model m,
                            Integer rid,
                            Neuron input,
                            boolean isNeg)

initActivation

public void initActivation(Iteration t,
                           Activation act)

Specified by:

initActivation in class Node

deleteActivation

public void deleteActivation(Iteration t,
                             Activation act)

Specified by:

deleteActivation in class Node

addActivation

public void addActivation(Iteration t,
                          Activation inputAct,
                          Range addedRange)

Specified by:

addActivation in interface Input

removeActivation

public void removeActivation(Iteration t,
                             Activation inputAct,
                             Range removedRange)

Specified by:

removeActivation in interface Input

getSign

public abstract int getSign()

isAllowedOption

public boolean isAllowedOption(Option n,
                               Activation act,
                               long v)

Specified by:

isAllowedOption in class Node

collectNodeAndRefinements

protected void collectNodeAndRefinements(AndNode.Refinement newRef,
                                         Set<AndNode.Refinement> inputs)

Specified by:

collectNodeAndRefinements in class LatticeNode

expandToNextLevel

public void expandToNextLevel(Iteration t,
                              Activation act,
                              Range addedRange,
                              Option removedConflict,
                              boolean train)

Specified by:

expandToNextLevel in class LatticeNode

Parameters:

t -

act -

addedRange -

removedConflict - This parameter contains a removed conflict if it is not null. In this case only expand activations that contain this removed conflict.

train -

computeSynapseWeightSum

public double computeSynapseWeightSum(Neuron n)

Specified by:

computeSynapseWeightSum in class Node

logicToString

public String logicToString()

Specified by:

logicToString in class Node