Node (aika 0.6 API)

java.lang.Object
- org.aika.lattice.Node

All Implemented Interfaces:

Comparable<Node>, Writable

Direct Known Subclasses:

AndNode, InputNode, OrNode
```
public abstract class Node
extends Object
implements Comparable<Node>, Writable
```
Author:

Lukas Molzberger

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`Node.ReverseAndRefinement`
`static class`	`Node.RidVisited`
`static class`	`Node.RSKey`
`static class`	`Node.Similarity`
`static class`	`Node.ThreadState`

Field Summary

Fields
Modifier and Type	Field and Description
`TreeMap<AndNode.Refinement,AndNode>`	`andChildren`
`static Comparator<Activation.Key>`	`BEGIN_COMP`
`static AtomicInteger`	`currentNodeId`
`static Comparator<Activation.Key>`	`END_COMP`
`boolean`	`endRequired`
`int`	`frequency`
`boolean`	`frequencyHasChanged`
`int`	`id`
`int`	`instanceSum`
`boolean`	`isBlocked`
`boolean`	`isQueued`
`boolean`	`isRemoved`
`int`	`isRemovedId`
`static int`	`isRemovedIdCounter`
`int`	`level`
`static boolean`	`LINK_NEURON_RELATIONS_OPTIMIZATION`
`ReadWriteLock`	`lock`
`boolean[]`	`matchRange`
`static org.aika.lattice.Node.DummyNode`	`MAX_NODE`
`static int`	`MAX_RID`
`static org.aika.lattice.Node.DummyNode`	`MIN_NODE`
`static int`	`minFrequency`
`Neuron`	`neuron`
`int`	`nOffset`
`double`	`nullHypFreq`
`int`	`numberOfNeuronRefs`
`double`	`oldNullHypFreq`
`TreeSet<OrNode.OrEntry>`	`orChildren`
`boolean`	`passive`
`long`	`queueId`
`Synapse.RangeVisibility[]`	`rangeVisibility`
`TreeMap<Node.ReverseAndRefinement,AndNode.Refinement>`	`reverseAndChildren`
`static Comparator<Activation.Key>`	`RID_COMP`
`boolean`	`ridRequired`
`int`	`sizeSum`
`Node.ThreadState[]`	`threads`
`static long`	`visitedCounter`

Constructor Summary

Constructors
Modifier Constructor and Description

protected Node()

Node(Iteration t, int level)

Constructors
Modifier	Constructor and Description
`protected`	`Node()`
	`Node(Iteration t, int level)`

Method Summary

All Methods Static Methods Instance Methods Abstract Methods Concrete Methods
Modifier and Type	Method and Description
`static void`	`addActivationAndPropagate(Iteration t, Activation.Key ak, Collection<Activation> inputActs)`
`Activation`	`addActivationInternal(Iteration t, Activation.Key ak, Collection<Activation> inputActs, boolean isTrainingAct)`
`void`	`addAndChild(AndNode.Refinement ref, AndNode child)`
`static void`	`addConflict(Iteration t, Option io, Option o, Activation act, Collection<Activation> inputActs, long v)`
`void`	`addOrChild(Iteration t, OrNode.OrEntry oe)`
`static boolean`	`adjust(Iteration t, Neuron neuron, int dir)`
`abstract void`	`apply(Iteration t, Activation act, Option conflict)`
`protected abstract void`	`changeNumberOfNeuronRefs(Iteration t, long v, int d)`
`abstract void`	`cleanup(Iteration t)`
`void`	`clearActivations(Iteration t)`
`void`	`clearActivations(Model m)`
`protected abstract Collection<AndNode.Refinement>`	`collectNodeAndRefinements(AndNode.Refinement newRef)`
`static int`	`compare(Node a, Node b)`
`int`	`compareTo(Node n)`
`boolean`	`computeAndParents(Iteration t, Integer offset, SortedSet<AndNode.Refinement> inputs, Map<AndNode.Refinement,Node> parents, boolean discoverPatterns, long v)`
`abstract void`	`computeNullHyp(Model m)`
`static void`	`computeRefinements(Iteration t, TreeSet<Node.RSKey> queue, Neuron n, Node.RSKey rsk, long v, List<Node.RSKey> outputs, List<Node.RSKey> cleanup)`
`abstract double`	`computeSynapseWeightSum(Integer offset, Neuron n)`
`void`	`count(Iteration t)`
`abstract void`	`deleteActivation(Iteration t, Activation act)`
`abstract void`	`discover(Iteration t, Activation act)`
`Collection<Activation>`	`getActivations(Iteration t)`
`AndNode`	`getAndChild(AndNode.Refinement ref)`
`Activation`	`getFirstActivation(Iteration t)`
`Node.ThreadState`	`getThreadState(Iteration t)`
`protected abstract boolean`	`hasSupport(Activation act)`
`abstract void`	`initActivation(Iteration t, Activation act)`
`abstract boolean`	`isAllowedOption(Iteration t, Option n, Activation act, long v)`
`boolean`	`isCovered(Iteration t, Integer offset, long v)`
`abstract boolean`	`isExpandable(boolean checkFrequency)`
`boolean`	`isFrequent()`
`boolean`	`isPublic()`
`boolean`	`isRequired()`
`abstract String`	`logicToString()`
`protected void`	`postProcessRemovedActivation(Iteration t, Activation act, Collection<Activation> inputActs)`
`protected void`	`prepareResultsForPredefinedNodes(Iteration t, TreeSet<Node.RSKey> queue, long v, List<Node.RSKey> outputs, List<Node.RSKey> cleanup, Neuron n, Synapse s, Integer offset)`
`protected Range`	`preProcessAddedActivation(Iteration t, Activation.Key ak, Collection<Activation> inputActs)`
`void`	`processAddedActivation(Iteration t, Activation.Key ak, Collection<Activation> inputActs)`
`void`	`processChanges(Iteration t)`
`void`	`processRemovedActivation(Iteration t, Activation act, Collection<Activation> inputActs)`
`abstract void`	`propagateAddedActivation(Iteration t, Activation act, Option conflict)`
`abstract void`	`propagateRemovedActivation(Iteration t, Activation act)`
`static Node`	`read(DataInput in, Iteration t)`
`void`	`readFields(DataInput in, Iteration t)` Deserialize the fields of this object from `in`.
`void`	`remove(Iteration t)`
`static void`	`removeActivationAndPropagate(Iteration t, Activation act, Collection<Activation> inputActs)`
`boolean`	`removeActivationInternal(Iteration t, Activation act, Collection<Activation> inputActs)`
`void`	`removeAndChild(AndNode.Refinement ref)`
`static void`	`removeConflict(Iteration t, Option io, Option o, Activation act, Activation nAct, long v)`
`void`	`removeFromNextLevel(Iteration t, Activation iAct)`
`void`	`removeOrChild(Iteration t, OrNode.OrEntry oe)`
`String`	`toSimpleString()`
`String`	`toString()`
`String`	`weightsToString()`
`void`	`write(DataOutput out)` Serialize the fields of this object to `out`.

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

minFrequency
```
public static int minFrequency
```

MAX_RID
```
public static int MAX_RID
```

LINK_NEURON_RELATIONS_OPTIMIZATION

public static boolean LINK_NEURON_RELATIONS_OPTIMIZATION

MIN_NODE

public static final org.aika.lattice.Node.DummyNode MIN_NODE

MAX_NODE

public static final org.aika.lattice.Node.DummyNode MAX_NODE

currentNodeId

public static AtomicInteger currentNodeId

id
```
public int id
```

reverseAndChildren

public TreeMap<Node.ReverseAndRefinement,AndNode.Refinement> reverseAndChildren

andChildren

public TreeMap<AndNode.Refinement,AndNode> andChildren

orChildren

public TreeSet<OrNode.OrEntry> orChildren

level
```
public int level
```

passive
```
public boolean passive
```

frequency
```
public volatile int frequency
```

nullHypFreq
```
public volatile double nullHypFreq
```

oldNullHypFreq
```
public volatile double oldNullHypFreq
```

isBlocked
```
public boolean isBlocked
```

endRequired
```
public boolean endRequired
```

ridRequired
```
public boolean ridRequired
```

numberOfNeuronRefs
```
public int numberOfNeuronRefs
```

isRemoved
```
public volatile boolean isRemoved
```

isRemovedId
```
public volatile int isRemovedId
```

isRemovedIdCounter
```
public static int isRemovedIdCounter
```

frequencyHasChanged

public volatile boolean frequencyHasChanged

nOffset
```
public volatile int nOffset
```

sizeSum
```
public volatile int sizeSum
```

instanceSum
```
public volatile int instanceSum
```

lock
```
public ReadWriteLock lock
```

isQueued
```
public boolean isQueued
```

queueId
```
public long queueId
```

neuron
```
public Neuron neuron
```

rangeVisibility

public Synapse.RangeVisibility[] rangeVisibility

matchRange
```
public boolean[] matchRange
```

visitedCounter
```
public static long visitedCounter
```

threads
```
public Node.ThreadState[] threads
```

BEGIN_COMP

public static final Comparator<Activation.Key> BEGIN_COMP

END_COMP

public static final Comparator<Activation.Key> END_COMP

RID_COMP

public static final Comparator<Activation.Key> RID_COMP

Constructor Detail

Node
```
protected Node()
```

Node

public Node(Iteration t,
            int level)

Method Detail

getThreadState

public Node.ThreadState getThreadState(Iteration t)

propagateAddedActivation

public abstract void propagateAddedActivation(Iteration t,
                                              Activation act,
                                              Option conflict)

propagateRemovedActivation

public abstract void propagateRemovedActivation(Iteration t,
                                                Activation act)

isAllowedOption

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

cleanup

public abstract void cleanup(Iteration t)

initActivation

public abstract void initActivation(Iteration t,
                                    Activation act)

deleteActivation

public abstract void deleteActivation(Iteration t,
                                      Activation act)

computeSynapseWeightSum

public abstract double computeSynapseWeightSum(Integer offset,
                                               Neuron n)

logicToString

public abstract String logicToString()

apply

public abstract void apply(Iteration t,
                           Activation act,
                           Option conflict)

discover

public abstract void discover(Iteration t,
                              Activation act)

collectNodeAndRefinements

protected abstract Collection<AndNode.Refinement> collectNodeAndRefinements(AndNode.Refinement newRef)

changeNumberOfNeuronRefs

protected abstract void changeNumberOfNeuronRefs(Iteration t,
                                                 long v,
                                                 int d)

hasSupport

protected abstract boolean hasSupport(Activation act)

computeNullHyp

public abstract void computeNullHyp(Model m)

isExpandable

public abstract boolean isExpandable(boolean checkFrequency)

addOrChild

public void addOrChild(Iteration t,
                       OrNode.OrEntry oe)

removeOrChild

public void removeOrChild(Iteration t,
                          OrNode.OrEntry oe)

addAndChild

public void addAndChild(AndNode.Refinement ref,
                        AndNode child)

removeAndChild

public void removeAndChild(AndNode.Refinement ref)

count
```
public void count(Iteration t)
```

addActivationInternal

public Activation addActivationInternal(Iteration t,
                                        Activation.Key ak,
                                        Collection<Activation> inputActs,
                                        boolean isTrainingAct)

removeActivationInternal

public boolean removeActivationInternal(Iteration t,
                                        Activation act,
                                        Collection<Activation> inputActs)

addConflict

public static void addConflict(Iteration t,
                               Option io,
                               Option o,
                               Activation act,
                               Collection<Activation> inputActs,
                               long v)

removeConflict

public static void removeConflict(Iteration t,
                                  Option io,
                                  Option o,
                                  Activation act,
                                  Activation nAct,
                                  long v)

processChanges

public void processChanges(Iteration t)

addActivationAndPropagate

public static void addActivationAndPropagate(Iteration t,
                                             Activation.Key ak,
                                             Collection<Activation> inputActs)

preProcessAddedActivation

protected Range preProcessAddedActivation(Iteration t,
                                          Activation.Key ak,
                                          Collection<Activation> inputActs)

processAddedActivation

public void processAddedActivation(Iteration t,
                                   Activation.Key ak,
                                   Collection<Activation> inputActs)

removeActivationAndPropagate

public static void removeActivationAndPropagate(Iteration t,
                                                Activation act,
                                                Collection<Activation> inputActs)

postProcessRemovedActivation

protected void postProcessRemovedActivation(Iteration t,
                                            Activation act,
                                            Collection<Activation> inputActs)

processRemovedActivation

public void processRemovedActivation(Iteration t,
                                     Activation act,
                                     Collection<Activation> inputActs)

getActivations

public Collection<Activation> getActivations(Iteration t)

getFirstActivation

public Activation getFirstActivation(Iteration t)

clearActivations

public void clearActivations(Iteration t)

clearActivations

public void clearActivations(Model m)

isFrequent
```
public boolean isFrequent()
```

isPublic
```
public boolean isPublic()
```

computeAndParents

public boolean computeAndParents(Iteration t,
                                 Integer offset,
                                 SortedSet<AndNode.Refinement> inputs,
                                 Map<AndNode.Refinement,Node> parents,
                                 boolean discoverPatterns,
                                 long v)

removeFromNextLevel

public void removeFromNextLevel(Iteration t,
                                Activation iAct)

remove
```
public void remove(Iteration t)
```

getAndChild

public AndNode getAndChild(AndNode.Refinement ref)

adjust

public static boolean adjust(Iteration t,
                             Neuron neuron,
                             int dir)

computeRefinements

public static void computeRefinements(Iteration t,
                                      TreeSet<Node.RSKey> queue,
                                      Neuron n,
                                      Node.RSKey rsk,
                                      long v,
                                      List<Node.RSKey> outputs,
                                      List<Node.RSKey> cleanup)

prepareResultsForPredefinedNodes

protected void prepareResultsForPredefinedNodes(Iteration t,
                                                TreeSet<Node.RSKey> queue,
                                                long v,
                                                List<Node.RSKey> outputs,
                                                List<Node.RSKey> cleanup,
                                                Neuron n,
                                                Synapse s,
                                                Integer offset)

isCovered

public boolean isCovered(Iteration t,
                         Integer offset,
                         long v)

isRequired
```
public boolean isRequired()
```

toString
```
public String toString()
```
Overrides:

toString in class Object

toSimpleString
```
public String toSimpleString()
```

weightsToString
```
public String weightsToString()
```

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

Parameters:

out - DataOuput to serialize this object into.

Throws:

IOException

readFields
```
public void readFields(DataInput in,
                       Iteration t)
                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

Parameters:

in - DataInput to deseriablize this object from.

Throws:

IOException

read

public static Node read(DataInput in,
                        Iteration t)
                 throws IOException

Throws:: IOException

compareTo
```
public int compareTo(Node n)
```
Specified by:

compareTo in interface Comparable<Node>

compare

public static int compare(Node a,
                          Node b)

Class Node

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

minFrequency

MAX_RID

LINK_NEURON_RELATIONS_OPTIMIZATION

MIN_NODE

MAX_NODE

currentNodeId

id

reverseAndChildren

andChildren

orChildren

level

passive

frequency

nullHypFreq

oldNullHypFreq

isBlocked

endRequired

ridRequired

numberOfNeuronRefs

isRemoved

isRemovedId

isRemovedIdCounter

frequencyHasChanged

nOffset

sizeSum

instanceSum

lock

isQueued

queueId

neuron

rangeVisibility

matchRange

visitedCounter

threads

BEGIN_COMP

END_COMP

RID_COMP

Constructor Detail

Node

Node

Method Detail

getThreadState

propagateAddedActivation

propagateRemovedActivation

isAllowedOption

cleanup

initActivation

deleteActivation

computeSynapseWeightSum

logicToString

apply

discover

collectNodeAndRefinements

changeNumberOfNeuronRefs

hasSupport

computeNullHyp

isExpandable

addOrChild

removeOrChild

addAndChild

removeAndChild

count

addActivationInternal

removeActivationInternal

addConflict

removeConflict

processChanges

addActivationAndPropagate

preProcessAddedActivation

processAddedActivation

removeActivationAndPropagate

postProcessRemovedActivation

processRemovedActivation