| Package | Description |
|---|---|
| org.aika | |
| org.aika.lattice | |
| org.aika.neuron | |
| org.aika.neuron.activation | |
| org.aika.training |
| Modifier and Type | Field and Description |
|---|---|
TreeMap<NodeActivation.Key,Activation> |
Document.activationsByRangeBegin |
TreeMap<NodeActivation.Key,Activation> |
Document.activationsByRangeEnd |
TreeMap<NodeActivation.Key,Activation> |
Document.activationsByRid |
ArrayList<Activation> |
Document.addedActivations |
TreeSet<Activation> |
Document.inputNeuronActivations |
ArrayDeque<Activation> |
Document.UpperBoundQueue.queue |
ArrayList<TreeSet<Activation>> |
Document.ValueQueue.queue |
| Modifier and Type | Method and Description |
|---|---|
Stream<Activation> |
Document.getActivations() |
Stream<Activation> |
Document.getFinalActivations() |
| Modifier and Type | Method and Description |
|---|---|
void |
Document.UpperBoundQueue.add(Activation act) |
void |
Document.ValueQueue.add(int round,
Activation act) |
void |
Document.ValueQueue.propagateActivationValue(int round,
Activation act) |
| Modifier and Type | Method and Description |
|---|---|
Activation |
OrNode.createActivation(Document doc,
NodeActivation.Key ak) |
Activation |
OrNode.lookupOrOption(Document doc,
Range r,
boolean create) |
| Modifier and Type | Method and Description |
|---|---|
void |
InputNode.addActivation(Document doc,
Activation inputAct) |
void |
OrNode.apply(Activation act) |
void |
OrNode.propagate(Activation act) |
| Modifier and Type | Field and Description |
|---|---|
TreeMap<NodeActivation.Key,Activation> |
INeuron.ThreadState.activations |
TreeMap<NodeActivation.Key,Activation> |
INeuron.ThreadState.activationsEnd |
TreeMap<NodeActivation.Key,Activation> |
INeuron.ThreadState.activationsRid |
| Modifier and Type | Method and Description |
|---|---|
Activation |
Neuron.addInput(Document doc,
Activation.Builder inputAct)
Propagate an input activation into the network.
|
Activation |
INeuron.addInput(Document doc,
Activation.Builder input)
Propagate an input activation into the network.
|
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,
Integer relationalId)
Propagate an input activation into the network.
|
Activation |
INeuron.getFirstActivation(Document doc) |
| Modifier and Type | Method and Description |
|---|---|
Collection<Activation> |
INeuron.getActivations(Document doc) |
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. |
Collection<Activation> |
INeuron.getFinalActivations(Document doc) |
Stream<Activation> |
INeuron.getFinalActivationsStream(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.propagate(Activation act) |
void |
INeuron.register(Activation act) |
| Modifier and Type | Field and Description |
|---|---|
Activation |
Candidate.activation |
Activation |
Activation.SynapseActivation.input |
Activation |
Activation.SynapseActivation.output |
| Modifier and Type | Field and Description |
|---|---|
static Comparator<Activation> |
Activation.ACTIVATION_ID_COMP |
Map<Activation,Activation.StateChange> |
SearchNode.modifiedActs |
SortedSet<Activation> |
Conflicts.primary |
Set<Activation> |
Conflicts.secondary |
| Modifier and Type | Method and Description |
|---|---|
static Activation |
Selector.get(Document doc,
INeuron n,
Integer rid,
Range r,
Range.Relation rr) |
static Activation |
Selector.get(Document doc,
INeuron n,
NodeActivation.Key ak) |
Activation |
Activation.StateChange.getActivation() |
| Modifier and Type | Method and Description |
|---|---|
static Collection<Activation> |
Selector.getActivationsByRange(INeuron.ThreadState th,
INeuron n,
Range r,
Range.Relation rr) |
static Collection<Activation> |
Selector.getActivationsByRangeEquals(INeuron.ThreadState th,
INeuron n,
Range r,
Range.Relation rr) |
static Collection<Activation> |
Conflicts.getConflicting(Activation n) |
static Stream<Activation> |
Selector.select(Document doc,
INeuron n,
Integer rid,
Range r,
Range.Relation rr) |
static Stream<Activation> |
Selector.select(INeuron.ThreadState th,
INeuron n,
Integer rid,
Range r,
Range.Relation rr) |
static Collection<Activation> |
Selector.select(Linker.SortGroup sortGroup,
Activation act) |
| Modifier and Type | Method and Description |
|---|---|
static void |
Conflicts.add(Activation primary,
Activation secondary) |
static boolean |
Activation.checkSelfReferencing(Activation nx,
Activation ny,
boolean onlySelected,
int depth) |
static Collection<Activation> |
Conflicts.getConflicting(Activation n) |
static void |
SearchNode.invalidateCachedDecision(Activation n) |
static boolean |
Conflicts.isConflicting(Activation a,
Activation b) |
static void |
Linker.link(Activation act)
Adds the incoming and outgoing links between neuron activations.
|
static void |
Conflicts.linkConflicts(Activation act,
long v,
Linker.Direction dir) |
static Collection<Activation> |
Selector.select(Linker.SortGroup sortGroup,
Activation act) |
| Modifier and Type | Method and Description |
|---|---|
void |
Activation.saveOldState(Map<Activation,Activation.StateChange> changes,
long v) |
| Constructor and Description |
|---|
Candidate(Activation act,
int id) |
SynapseActivation(Synapse s,
Activation input,
Activation output) |
| Modifier and Type | Field and Description |
|---|---|
TreeSet<Activation> |
SupervisedTraining.errorSignalActivations |
TreeSet<Activation> |
SupervisedTraining.BackPropagationQueue.queue |
TreeSet<Activation> |
SupervisedTraining.targetActivations |
| Modifier and Type | Method and Description |
|---|---|
void |
SupervisedTraining.BackPropagationQueue.add(Activation act) |
void |
SupervisedTraining.computeBackpropagationErrorSignal(Activation act) |
void |
SupervisedTraining.computeOutputErrorSignal(Activation act) |
SynapseEvaluation.Result |
SynapseEvaluation.evaluate(Synapse s,
Activation iAct,
Activation oAct)
Determines whether a synapse should be created between two neurons during training.
|
static void |
LongTermLearning.longTermDepression(Document doc,
LongTermLearning.Config config,
Activation act,
boolean dir)
The long-term depression algorithm decreases the strength of a synapse if only one side of the synapse is
firing.
|
static void |
LongTermLearning.longTermPotentiation(Document doc,
LongTermLearning.Config config,
Activation act)
The long-term potentiation algorithm is a variant of the Hebb learning rule.
|
void |
SupervisedTraining.train(INeuron n,
Activation targetAct,
double learnRate,
SynapseEvaluation se) |
void |
SupervisedTraining.updateErrorSignal(Activation act) |
Copyright © 2018. All rights reserved.