public class Neuron extends Provider<INeuron>
Neuron class is a proxy implementation for the real neuron implementation in the class INeuron.
Aika uses the provider pattern to store and reload rarely used neurons or logic nodes.| Modifier and Type | Field and Description |
|---|---|
NavigableMap<Synapse,Synapse> |
inMemoryInputSynapses |
NavigableMap<Synapse,Synapse> |
inMemoryOutputSynapses |
ReadWriteLock |
lock |
| Constructor and Description |
|---|
Neuron(Model m,
INeuron n) |
Neuron(Model m,
int id) |
| Modifier and Type | Method and Description |
|---|---|
Activation |
addInput(Document doc,
int begin,
int end)
Propagate an input activation into the network.
|
Activation |
addInput(Document doc,
int begin,
int end,
Integer rid)
Propagate an input activation into the network.
|
Activation |
addInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o)
Propagate an input activation into the network.
|
Activation |
addInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o,
double value)
Propagate an input activation into the network.
|
Activation |
addInput(Document doc,
int begin,
int end,
InterprNode o)
Propagate an input activation into the network.
|
Collection<Activation> |
getFinalActivations(Document doc)
getFinalActivations is a convenience method to retrieve all activations of the given neuron that
are part of the final interpretation. |
void |
removeInput(Document doc,
int begin,
int end) |
void |
removeInput(Document doc,
int begin,
int end,
Integer rid) |
void |
removeInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o) |
void |
removeInput(Document doc,
int begin,
int end,
InterprNode o) |
compareTo, discard, equals, get, getIfNotSuspended, hashCode, isSuspended, setModified, suspend, toStringpublic ReadWriteLock lock
public NavigableMap<Synapse,Synapse> inMemoryInputSynapses
public NavigableMap<Synapse,Synapse> inMemoryOutputSynapses
public Activation addInput(Document doc, int begin, int end)
doc - The current documentbegin - The range beginend - The range endpublic Activation addInput(Document doc, int begin, int end, InterprNode o)
doc - The current documentbegin - The range beginend - The range endo - The interpretation nodepublic Activation addInput(Document doc, int begin, int end, Integer rid)
doc - The current documentbegin - The range beginend - The range endrid - The relational id (e.g. the word position)public Activation addInput(Document doc, int begin, int end, Integer rid, InterprNode o)
doc - The current documentbegin - The range beginend - The range endrid - The relational id (e.g. the word position)o - The interpretation nodepublic Activation addInput(Document doc, int begin, int end, Integer rid, InterprNode o, double value)
doc - The current documentbegin - The range beginend - The range endrid - The relational id (e.g. the word position)o - The interpretation nodevalue - The activation value of this input activationpublic void removeInput(Document doc, int begin, int end)
public void removeInput(Document doc, int begin, int end, InterprNode o)
public void removeInput(Document doc, int begin, int end, Integer rid, InterprNode o)
public Collection<Activation> getFinalActivations(Document doc)
getFinalActivations is a convenience method to retrieve all activations of the given neuron that
are part of the final interpretation. Before calling this method, the doc.process() needs to
be called first. getFinalActivations requires that the doc.process() method has been called first.doc - The current documentCopyright © 2017. All rights reserved.