| Package | Description |
|---|---|
| org.aika | |
| org.aika.corpus | |
| org.aika.lattice | |
| org.aika.neuron | |
| org.aika.training |
| Modifier and Type | Method and Description |
|---|---|
<P extends Provider<? extends Node>> |
Model.lookupNodeProvider(int id) |
| Modifier and Type | Field and Description |
|---|---|
TreeSet<Node> |
Document.addedNodes |
TreeSet<Node> |
Document.Queue.queue |
| Modifier and Type | Method and Description |
|---|---|
void |
Document.Queue.add(Node n) |
| Modifier and Type | Class and Description |
|---|---|
class |
Node<T extends Node,A extends NodeActivation<T>>
The
Node class is the abstract class for all the boolean logic nodes underneath the neural network layer. |
static class |
Node.ThreadState<T extends Node,A extends NodeActivation<T>>
The
ThreadState is a thread local data structure containing the activations of a single document for
a specific logic node. |
class |
NodeActivation<T extends Node> |
static class |
NodeActivation.Key<T extends Node> |
| Modifier and Type | Class and Description |
|---|---|
class |
AndNode
The
InputNode and the AndNode classes together form a pattern lattice, containing all
possible substructures of any given conjunction. |
class |
InputNode
The
InputNode class is the input layer for the boolean logic. |
class |
OrNode
While several neurons might share a the same input-node or and-node, there is always a always a one-to-one relation
between or-nodes and neurons.
|
| Modifier and Type | Field and Description |
|---|---|
static Node |
Node.MAX_NODE |
static Node |
Node.MIN_NODE |
T |
NodeActivation.Key.node |
Node |
OrNode.requiredNode |
| Modifier and Type | Field and Description |
|---|---|
TreeMap<Integer,TreeSet<Provider<Node>>> |
OrNode.allParents |
TreeMap<Integer,TreeSet<Provider<Node>>> |
OrNode.parents |
SortedMap<AndNode.Refinement,Provider<? extends Node>> |
AndNode.parents |
| Modifier and Type | Method and Description |
|---|---|
static <T extends Node,A extends NodeActivation<T>> |
Node.addActivationAndPropagate(Document doc,
NodeActivation.Key<T> ak,
Collection<NodeActivation<?>> inputActs)
Add a new activation to this logic node and further propagate this activation through the network.
|
| Modifier and Type | Method and Description |
|---|---|
static Node |
Node.readNode(DataInput in,
Provider p) |
| Modifier and Type | Method and Description |
|---|---|
static SortedMap<AndNode.Refinement,Provider<? extends Node>> |
AndNode.computeNextLevelParents(Model m,
int threadId,
Node pa,
AndNode.Refinement ref,
PatternDiscovery.Config config) |
| Modifier and Type | Method and Description |
|---|---|
void |
OrNode.addInput(Integer ridOffset,
int threadId,
Node in,
boolean all) |
int |
Node.compareTo(Node n) |
static SortedMap<AndNode.Refinement,Provider<? extends Node>> |
AndNode.computeNextLevelParents(Model m,
int threadId,
Node pa,
AndNode.Refinement ref,
PatternDiscovery.Config config) |
static AndNode |
AndNode.createNextLevelNode(Model m,
int threadId,
Node n,
AndNode.Refinement ref,
PatternDiscovery.Config config) |
static void |
OrNode.processCandidate(Document doc,
Node<?,? extends NodeActivation<?>> parentNode,
NodeActivation inputAct,
boolean train) |
void |
OrNode.removeInput(Integer ridOffset,
int threadId,
Node in,
boolean all) |
| Constructor and Description |
|---|
AndNode(Model m,
int level,
SortedMap<AndNode.Refinement,Provider<? extends Node>> parents) |
| Modifier and Type | Method and Description |
|---|---|
<T extends Node> |
Activation.filter(T n,
Integer rid,
Range r,
Range.Relation rr,
InterpretationNode o,
InterpretationNode.Relation or) |
| Modifier and Type | Method and Description |
|---|---|
boolean |
PatternDiscovery.PatternEvaluation.evaluate(Node n)
Check if
node is an interesting pattern that might be considered for further processing. |
Copyright © 2018. All rights reserved.