public final class Activation extends NodeActivation<OrNode>
Activation class is the most central class in Aika. On the one hand it stores the activation value
for a given neuron in the State substructure. On the other hand it specifies where this activation is
located within the document and to which interpretation it belongs. The Activation.Key therefore
consists of the logic node to which this activation belongs. If this logic node is an or-node, then this activation
automatically also belongs to the neuron as well. Furthermore, the key contains the char range within the document
and the relational id (rid). The relational id might be used to store the word pos for instance. Lastly, the key
contain the interpretation node of this activation, specifying to which interpretation this activation belongs.
The activations are linked to each other on two levels. The fields inputs and outputs
contain the activation links within the logic layer. The fields neuronInputs and
neuronOutputs contain the links on the neural layer.
| Modifier and Type | Class and Description |
|---|---|
static class |
Activation.Builder |
static class |
Activation.Mode |
static class |
Activation.Rounds
Since Aika is a recurrent neural network, it is necessary to compute several rounds of activation values.
|
static class |
Activation.State
A
State object contains the activation value of an activation object that belongs to a neuron. |
class |
Activation.StateChange
The
StateChange class is used to store the state change of an activation that occurs in each node of
the binary search tree. |
static class |
Activation.SynapseActivation
The
SynapseActivation mirror the synapse link in the network of activations. |
NodeActivation.Key<T extends Node>| Modifier and Type | Field and Description |
|---|---|
Activation.StateChange |
currentStateChange |
long |
currentStateV |
double |
errorSignal |
Double |
inputValue |
boolean |
isQueued |
double |
lowerBound |
double |
maxActValue |
TreeSet<Activation.SynapseActivation> |
neuronInputs |
TreeSet<Activation.SynapseActivation> |
neuronOutputs |
long |
queueId |
Activation.Rounds |
rounds |
Integer |
sequence |
Double |
targetValue |
boolean |
ubQueued |
double |
upperBound |
| Constructor and Description |
|---|
Activation(int id,
Document doc,
NodeActivation.Key key) |
compare, compareTo, link, toStringpublic TreeSet<Activation.SynapseActivation> neuronInputs
public TreeSet<Activation.SynapseActivation> neuronOutputs
public Integer sequence
public double upperBound
public double lowerBound
public Activation.Rounds rounds
public double maxActValue
public boolean ubQueued
public boolean isQueued
public long queueId
public long currentStateV
public Activation.StateChange currentStateChange
public double errorSignal
public Double targetValue
public Double inputValue
public Activation(int id,
Document doc,
NodeActivation.Key key)
public void addSynapseActivation(int dir,
Activation.SynapseActivation sa)
public void removeSynapseActivation(int dir,
Activation.SynapseActivation sa)
public List<Activation.SynapseActivation> getFinalInputActivations()
public List<Activation.SynapseActivation> getFinalOutputActivations()
public boolean isFinalActivation()
public Activation.State getFinalState()
public static Activation get(Document doc, INeuron n, Integer rid, Range r, Range.Relation rr, InterpretationNode o, InterpretationNode.Relation or)
public static Activation get(Document doc, INeuron n, NodeActivation.Key ak)
public static Stream<Activation> select(Document doc, INeuron n, Integer rid, Range r, Range.Relation rr, InterpretationNode o, InterpretationNode.Relation or)
public static Stream<Activation> select(INeuron.ThreadState th, INeuron n, Integer rid, Range r, Range.Relation rr, InterpretationNode o, InterpretationNode.Relation or)
public static Stream<Activation> getActivationsByRange(INeuron.ThreadState th, INeuron n, Integer rid, Range r, Range.Relation rr, InterpretationNode o, InterpretationNode.Relation or)
public <T extends Node> boolean filter(T n, Integer rid, Range r, Range.Relation rr, InterpretationNode o, InterpretationNode.Relation or)
public Integer getSequence()
public String toString(SearchNode sn, boolean withWeights, boolean withTextSnipped, boolean withLogic)
public void saveOldState(List<Activation.StateChange> changes, long v)
public void saveNewState()
Copyright © 2018. All rights reserved.