Package network.aika.lattice
Class InputNode
- java.lang.Object
-
- network.aika.AbstractNode<Provider<T>>
-
- network.aika.lattice.Node<InputNode,InputActivation>
-
- network.aika.lattice.InputNode
-
- All Implemented Interfaces:
Comparable<Node>,Writable
public class InputNode extends Node<InputNode,InputActivation>
TheInputNodeclass is the input layer for the boolean logic. The input-node has two sources of activations. First, it might be underlying logic node of anInputNeuronin 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
-
-
Field Summary
Fields Modifier and Type Field Description static intCHILD_NODE_THRESHOLD-
Fields inherited from class network.aika.AbstractNode
lastUsedDocumentId, modified, provider
-
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description voidaddActivation(Activation inputAct)voidcleanup()voiddelete(Set<String> modelLabels)RefValueexpand(int threadId, Document doc, Refinement ref)StringlogicToString()protected voidpropagate(InputActivation act)Propagate an activation to the next node or the next neuron that is depending on the current node.voidreadFields(DataInput in, Model m)Deserialize the fields of this object fromin.voidreprocessInputs(Document doc)voidsetInputNeuron(Neuron n)voidwrite(DataOutput out)Serialize the fields of this object toout.-
Methods inherited from class network.aika.lattice.Node
addActivation, changeNumberOfNeuronRefs, clearActivations, clearActivations, clearActivations, clearThreadState, compareRank, compareTo, getActivations, getNeuronLabel, isNeuron, isQueued, isRequired, postCreate, processChanges, propagateToOrNode, readNode, register, remove, setNotQueued, toString
-
Methods inherited from class network.aika.AbstractNode
addModelLabel, getLabel, getModelLabels, getProvider, reactivate, read, setModified, suspend
-
-
-
-
Constructor Detail
-
InputNode
public InputNode()
-
InputNode
public InputNode(Model m)
-
-
Method Detail
-
setInputNeuron
public void setInputNeuron(Neuron n)
-
addActivation
public void addActivation(Activation inputAct)
-
reprocessInputs
public void reprocessInputs(Document doc)
- Specified by:
reprocessInputsin classNode<InputNode,InputActivation>
-
expand
public RefValue expand(int threadId, Document doc, Refinement ref)
-
propagate
protected void propagate(InputActivation act)
Description copied from class:NodePropagate an activation to the next node or the next neuron that is depending on the current node.- Specified by:
propagatein classNode<InputNode,InputActivation>- Parameters:
act-
-
cleanup
public void cleanup()
- Specified by:
cleanupin classNode<InputNode,InputActivation>
-
logicToString
public String logicToString()
- Specified by:
logicToStringin classNode<InputNode,InputActivation>
-
write
public void write(DataOutput out) throws IOException
Description copied from interface:WritableSerialize the fields of this object toout.- Specified by:
writein interfaceWritable- Overrides:
writein classNode<InputNode,InputActivation>- Parameters:
out-DataOuputto serialize this object into.- Throws:
IOException
-
readFields
public void readFields(DataInput in, Model m) throws IOException
Description copied from interface:WritableDeserialize the fields of this object fromin.For efficiency, implementations should attempt to re-use storage in the existing object where possible.
- Specified by:
readFieldsin interfaceWritable- Overrides:
readFieldsin classNode<InputNode,InputActivation>- Parameters:
in-DataInputto deseriablize this object from.- Throws:
IOException
-
-