| Package | Description |
|---|---|
| org.aika | |
| org.aika.corpus | |
| org.aika.lattice | |
| org.aika.neuron |
| Modifier and Type | Method and Description |
|---|---|
Activation |
Neuron.addInput(Document doc,
int begin,
int end)
Propagate an input activation into the network.
|
Activation |
Neuron.addInput(Document doc,
int begin,
int end,
double value,
Double targetValue)
Propagate an input activation into the network.
|
Activation |
Neuron.addInput(Document doc,
int begin,
int end,
Integer rid)
Propagate an input activation into the network.
|
Activation |
Neuron.addInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o)
Propagate an input activation into the network.
|
Activation |
Neuron.addInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o,
double value)
Propagate an input activation into the network.
|
Activation |
Neuron.addInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o,
double value,
Double targetValue)
Propagate an input activation into the network.
|
Activation |
Neuron.addInput(Document doc,
int begin,
int end,
InterprNode o)
Propagate an input activation into the network.
|
| Modifier and Type | Method and Description |
|---|---|
Collection<Activation> |
Neuron.getFinalActivations(Document doc)
getFinalActivations is a convenience method to retrieve all activations of the given neuron that
are part of the final interpretation. |
| Modifier and Type | Field and Description |
|---|---|
Activation |
SearchNode.StateChange.act |
Activation |
InterprNode.act |
| Modifier and Type | Field and Description |
|---|---|
TreeSet<Activation> |
Document.errorSignalActivations |
TreeSet<Activation> |
Document.inputNeuronActivations |
NavigableSet<Activation> |
InterprNode.neuronActivations |
ArrayDeque<Activation> |
Document.UpperBoundQueue.queue |
ArrayList<ArrayDeque<Activation>> |
Document.ValueQueue.queue |
TreeSet<Activation> |
Document.BackPropagationQueue.queue |
TreeSet<Activation> |
Document.targetActivations |
| Modifier and Type | Method and Description |
|---|---|
Collection<Activation> |
InterprNode.getNeuronActivations() |
| Modifier and Type | Method and Description |
|---|---|
void |
Document.UpperBoundQueue.add(Activation act) |
void |
Document.BackPropagationQueue.add(Activation act) |
void |
Document.ValueQueue.add(int round,
Activation act) |
Document.SynEvalResult |
Document.SynapseEvaluation.evaluate(Activation iAct,
Activation oAct)
Determines whether a synapse should be created between two neurons during training.
|
void |
Document.ValueQueue.propagateWeight(int round,
Activation act) |
static void |
SearchNode.StateChange.saveNewState(Activation act) |
static void |
SearchNode.StateChange.saveOldState(List<SearchNode.StateChange> changes,
Activation act,
long v) |
| Modifier and Type | Method and Description |
|---|---|
protected Activation |
OrNode.createActivation(Document doc,
NodeActivation.Key ak) |
| Modifier and Type | Method and Description |
|---|---|
void |
OrNode.apply(Document doc,
Activation act) |
void |
OrNode.propagateAddedActivation(Document doc,
Activation act) |
void |
OrNode.register(Activation act,
Document doc) |
| Modifier and Type | Field and Description |
|---|---|
Activation |
Activation.SynapseActivation.input |
Activation |
Activation.SynapseActivation.output |
| Modifier and Type | Method and Description |
|---|---|
Activation |
INeuron.addInput(Document doc,
int begin,
int end,
Integer rid,
InterprNode o,
double value,
Double targetValue)
Propagate an input activation into the network.
|
| Modifier and Type | Method and Description |
|---|---|
Collection<Activation> |
INeuron.getFinalActivations(Document doc)
getFinalActivations is a convenience method to retrieve all activations of the given neuron that
are part of the final interpretation. |
| Modifier and Type | Method and Description |
|---|---|
void |
INeuron.computeBackpropagationErrorSignal(Activation act) |
void |
INeuron.computeBounds(Activation act) |
void |
INeuron.computeOutputErrorSignal(Activation act) |
Activation.State |
INeuron.computeWeight(int round,
Activation act,
SearchNode sn) |
void |
INeuron.linkNeuronRelations(Document doc,
Activation act)
Sets the incoming and outgoing links between neuron activations.
|
void |
INeuron.propagateAddedActivation(Document doc,
Activation act) |
void |
INeuron.train(Document doc,
Activation targetAct,
double learnRate,
Document.SynapseEvaluation se) |
| Constructor and Description |
|---|
SynapseActivation(Synapse s,
Activation input,
Activation output) |
Copyright © 2017. All rights reserved.