org.aika.lattice

Class InputNode

java.lang.Object

org.aika.AbstractNode<Provider<T>>

org.aika.lattice.Node<InputNode,NodeActivation<InputNode>>

org.aika.lattice.InputNode

All Implemented Interfaces:

Comparable<Node>, Writable

public class InputNode
extends Node<InputNode,NodeActivation<InputNode>>

The InputNode class is the input layer for the boolean logic. The input-node has two sources of activations. First, it might be underlying logic node of an InputNeuron in which case the input activations come from the outside. The second option is that the activation come from the output of another neuron.

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
Neuron	inputNeuron
Synapse.Key	key
ReadWriteLock	synapseLock
Map<org.aika.lattice.InputNode.SynapseKey,Synapse>	synapses

Fields inherited from class org.aika.lattice.Node

allOrChildren, andChildren, BEGIN_COMP, END_COMP, isDiscovered, level, lock, MAX_NODE, MAX_RELATIVE_RID, MIN_NODE, numberOfNeuronRefs, orChildren, reverseAndChildren, RID_COMP, statistic, threads

Fields inherited from class org.aika.AbstractNode

lastUsedDocumentId, provider

Constructor Summary

Constructors

Constructor and Description
InputNode()
InputNode(Model m, Synapse.Key key)

Method Summary

Modifier and Type	Method and Description
static InputNode	add(Model m, Synapse.Key key, INeuron input)
void	addActivation(Document doc, NodeActivation inputAct)
void	cleanup()
double	computeSynapseWeightSum(Integer offset, INeuron n)
protected NodeActivation<InputNode>	createActivation(Document doc, NodeActivation.Key ak)
void	discover(Document doc, NodeActivation<InputNode> act, PatternDiscovery.Config config)
Synapse	getSynapse(Integer rid, Neuron outputNeuron)
boolean	isAllowedOption(int threadId, InterpretationNode n, NodeActivation act, long v)
String	logicToString()
void	propagateAddedActivation(Document doc, NodeActivation act) Propagate an activation to the next node or the next neuron that is depending on the current node.
void	readFields(DataInput in, Model m) Deserialize the fields of this object from in.
void	remove()
void	removeSynapse(Synapse s)
void	setSynapse(Synapse s)
void	write(DataOutput out) Serialize the fields of this object to out.

Methods inherited from class org.aika.lattice.Node

addActivationAndPropagate, changeNumberOfNeuronRefs, compareTo, getNeuronLabel, getThreadState, isRequired, processChanges, readNode, register, toString, weightsToString

Methods inherited from class org.aika.AbstractNode

reactivate, read, setModified, suspend

Methods inherited from class java.lang.Object

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

Field Detail

key

public Synapse.Key key

inputNeuron

public Neuron inputNeuron

synapses

public Map<org.aika.lattice.InputNode.SynapseKey,Synapse> synapses

synapseLock

public ReadWriteLock synapseLock

Constructor Detail

InputNode

public InputNode()

InputNode

public InputNode(Model m,
                 Synapse.Key key)

Method Detail

add

public static InputNode add(Model m,
                            Synapse.Key key,
                            INeuron input)

createActivation

protected NodeActivation<InputNode> createActivation(Document doc,
                                                     NodeActivation.Key ak)

addActivation

public void addActivation(Document doc,
                          NodeActivation inputAct)

propagateAddedActivation

public void propagateAddedActivation(Document doc,
                                     NodeActivation act)

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<InputNode,NodeActivation<InputNode>>

isAllowedOption

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

Specified by:

isAllowedOption in class Node<InputNode,NodeActivation<InputNode>>

discover

public void discover(Document doc,
                     NodeActivation<InputNode> act,
                     PatternDiscovery.Config config)

Specified by:

discover in class Node<InputNode,NodeActivation<InputNode>>

computeSynapseWeightSum

public double computeSynapseWeightSum(Integer offset,
                                      INeuron n)

Specified by:

computeSynapseWeightSum in class Node<InputNode,NodeActivation<InputNode>>

getSynapse

public Synapse getSynapse(Integer rid,
                          Neuron outputNeuron)

setSynapse

public void setSynapse(Synapse s)

removeSynapse

public void removeSynapse(Synapse s)

cleanup

public void cleanup()

Specified by:

cleanup in class Node<InputNode,NodeActivation<InputNode>>

remove

public void remove()

Overrides:

remove in class Node<InputNode,NodeActivation<InputNode>>

logicToString

public String logicToString()

Specified by:

logicToString in class Node<InputNode,NodeActivation<InputNode>>

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<InputNode,NodeActivation<InputNode>>

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<InputNode,NodeActivation<InputNode>>

Parameters:

in - DataInput to deseriablize this object from.

Throws:

IOException