INeuron (aika 0.19 API)

java.lang.Object
- network.aika.AbstractNode<Neuron,Activation>
- - network.aika.neuron.INeuron

All Implemented Interfaces:

Comparable<INeuron>, Writable
```
public class INeuron
extends AbstractNode<Neuron,Activation>
implements Comparable<INeuron>
```
The INeuron class represents a internal neuron implementation in Aikas neural network and is connected to other neurons through input synapses and output synapses. The activation value of a neuron is calculated by computing the weighted sum (input act. value * synapse weight) of the input synapses, adding the bias to it and sending the resulting value through a transfer function (the upper part of tanh).

The neuron does not store its activations by itself. The activation objects are stored within the logic nodes. To access the activations of this neuron simply use the member variable node or use the method getFinalActivations(Document doc) to ge the final activations of this neuron.

Author:

Lukas Molzberger

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`INeuron.ActKey`
`static class`	`INeuron.LogicType`
`static class`	`INeuron.ThreadState` The `ThreadState` is a thread local data structure containing the activations of a single document for a specific logic node.
`static class`	`INeuron.Type`

Field Summary

Fields
Modifier and Type	Field and Description
`ActivationFunction`	`activationFunction`
`static boolean`	`ALLOW_WEAK_NEGATIVE_WEIGHTS`
`static Comparator<INeuron.ActKey>`	`BEGIN_COMP`
`double`	`bias`
`double`	`biasDelta`
`double`	`biasSum`
`double`	`biasSumDelta`
`static Comparator<INeuron.ActKey>`	`END_COMP`
`TreeMap<Synapse,Synapse>`	`inputSynapses`
`boolean`	`isMeta`
`String`	`label`
`ReadWriteLock`	`lock`
`INeuron.LogicType`	`logicType`
`double`	`metaBias`
`double`	`negDirSum`
`double`	`negRecSum`
`Provider<OrNode>`	`node`
`int`	`numberOfInputSynapses`
`int`	`numDisjunctiveSynapses`
`Provider<InputNode>`	`outputNode`
`Map<Integer,Relation>`	`outputRelations`
`TreeMap<Synapse,Synapse>`	`outputSynapses`
`String`	`outputText`
`PassiveInputFunction`	`passiveInputFunction`
`TreeMap<Synapse,Synapse>`	`passiveInputSynapses`
`double`	`posDirSum`
`double`	`posPassiveSum`
`double`	`posRecSum`
`double`	`requiredSum`
`Writable`	`statistic`
`INeuron.ThreadState[]`	`threads`
`static double`	`TOLERANCE`
`INeuron.Type`	`type`
`static double`	`WEIGHT_TOLERANCE`

Fields inherited from class network.aika.AbstractNode
lastUsedDocumentId, modified, provider

Constructor Summary

Constructors
Constructor and Description

INeuron(Model m)

INeuron(Model m, String label)

INeuron(Model m, String label, String outputText)

Constructors
Constructor and Description
`INeuron(Model m)`
`INeuron(Model m, String label)`
`INeuron(Model m, String label, String outputText)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`Activation`	`addInput(Document doc, Activation.Builder input)` Propagate an input activation into the network.
`void`	`changeBias(double bd)`
`void`	`clearActivations()`
`void`	`clearActivations(Document doc)`
`void`	`clearActivations(int threadId)`
`int`	`compareTo(INeuron n)`
`Activation`	`getActivation(Document doc, Range r, boolean onlyFinal)`
`Collection<Activation>`	`getActivations(Document doc, boolean onlyFinal)`
`double`	`getNewBiasSum()`
`INeuron.ThreadState`	`getThreadState(int threadId, boolean create)`
`boolean`	`isPassiveInputNeuron()`
`void`	`propagate(Activation act)` Propagate an activation to the next node or the next neuron that is depending on the current node.
`void`	`reactivate()`
`void`	`readFields(DataInput in, Model m)` Deserialize the fields of this object from `in`.
`static INeuron`	`readNeuron(DataInput in, Neuron p)`
`void`	`register(Activation act)`
`void`	`registerPassiveInputSynapse(Synapse s)`
`void`	`remove()`
`void`	`setBias(double b)`
`void`	`suspend()`
`String`	`toString()`
`String`	`toStringWithSynapses()`
`static boolean`	`update(int threadId, Document doc, Neuron pn, Double bias, Collection<Synapse> modifiedSynapses)`
`void`	`write(DataOutput out)` Serialize the fields of this object to `out`.

Methods inherited from class network.aika.AbstractNode
read, setModified

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Field Detail

ALLOW_WEAK_NEGATIVE_WEIGHTS

public static boolean ALLOW_WEAK_NEGATIVE_WEIGHTS

WEIGHT_TOLERANCE
```
public static double WEIGHT_TOLERANCE
```

TOLERANCE
```
public static double TOLERANCE
```

label
```
public String label
```

type
```
public INeuron.Type type
```

logicType
```
public INeuron.LogicType logicType
```

outputText
```
public String outputText
```

bias
```
public volatile double bias
```

biasDelta
```
public volatile double biasDelta
```

biasSum
```
public volatile double biasSum
```

biasSumDelta
```
public volatile double biasSumDelta
```

posDirSum
```
public volatile double posDirSum
```

negDirSum
```
public volatile double negDirSum
```

negRecSum
```
public volatile double negRecSum
```

posRecSum
```
public volatile double posRecSum
```

posPassiveSum
```
public volatile double posPassiveSum
```

requiredSum
```
public volatile double requiredSum
```

metaBias
```
public volatile double metaBias
```

isMeta
```
public volatile boolean isMeta
```

numDisjunctiveSynapses

public volatile int numDisjunctiveSynapses

statistic
```
public Writable statistic
```

activationFunction

public ActivationFunction activationFunction

numberOfInputSynapses
```
public int numberOfInputSynapses
```

outputRelations

public Map<Integer,Relation> outputRelations

inputSynapses

public TreeMap<Synapse,Synapse> inputSynapses

outputSynapses

public TreeMap<Synapse,Synapse> outputSynapses

passiveInputSynapses

public TreeMap<Synapse,Synapse> passiveInputSynapses

outputNode
```
public Provider<InputNode> outputNode
```

node
```
public Provider<OrNode> node
```

lock
```
public ReadWriteLock lock
```

passiveInputFunction

public PassiveInputFunction passiveInputFunction

threads
```
public INeuron.ThreadState[] threads
```

BEGIN_COMP

public static final Comparator<INeuron.ActKey> BEGIN_COMP

END_COMP

public static final Comparator<INeuron.ActKey> END_COMP

Constructor Detail

INeuron
```
public INeuron(Model m)
```

INeuron

public INeuron(Model m,
               String label)

INeuron

public INeuron(Model m,
               String label,
               String outputText)

Method Detail

getThreadState

public INeuron.ThreadState getThreadState(int threadId,
                                          boolean create)

addInput

public Activation addInput(Document doc,
                           Activation.Builder input)

Propagate an input activation into the network.

Parameters:: doc - The current document; input -

remove
```
public void remove()
```

propagate
```
public void propagate(Activation act)
```
Description copied from class: AbstractNode

Propagate an activation to the next node or the next neuron that is depending on the current node.

Specified by:

propagate in class AbstractNode<Neuron,Activation>

getActivations

public Collection<Activation> getActivations(Document doc,
                                             boolean onlyFinal)

getActivation

public Activation getActivation(Document doc,
                                Range r,
                                boolean onlyFinal)

clearActivations
```
public void clearActivations()
```

clearActivations

public void clearActivations(Document doc)

clearActivations

public void clearActivations(int threadId)

compareTo
```
public int compareTo(INeuron n)
```
Specified by:

compareTo in interface Comparable<INeuron>

write
```
public void write(DataOutput out)
           throws IOException
```
Description copied from interface: Writable

Serialize the fields of this object to out.

Specified by:

write in interface Writable

Parameters:

out - DataOuput to serialize this object into.

Throws:

IOException

readFields
```
public void readFields(DataInput in,
                       Model m)
                throws IOException
```
Description copied from interface: Writable

Deserialize the fields of this object from in.
For efficiency, implementations should attempt to re-use storage in the existing object where possible.

Specified by:

readFields in interface Writable

Parameters:

in - DataInput to deseriablize this object from.

Throws:

IOException

suspend
```
public void suspend()
```
Overrides:

suspend in class AbstractNode<Neuron,Activation>

reactivate
```
public void reactivate()
```
Overrides:

reactivate in class AbstractNode<Neuron,Activation>

setBias
```
public void setBias(double b)
```

changeBias
```
public void changeBias(double bd)
```

getNewBiasSum
```
public double getNewBiasSum()
```

update

public static boolean update(int threadId,
                             Document doc,
                             Neuron pn,
                             Double bias,
                             Collection<Synapse> modifiedSynapses)

readNeuron

public static INeuron readNeuron(DataInput in,
                                 Neuron p)
                          throws IOException

Throws:: IOException

isPassiveInputNeuron
```
public boolean isPassiveInputNeuron()
```

registerPassiveInputSynapse

public void registerPassiveInputSynapse(Synapse s)

toString
```
public String toString()
```
Overrides:

toString in class Object

toStringWithSynapses
```
public String toStringWithSynapses()
```

Class INeuron

Nested Class Summary

Field Summary

Fields inherited from class network.aika.AbstractNode

Constructor Summary

Method Summary

Methods inherited from class network.aika.AbstractNode

Methods inherited from class java.lang.Object

Field Detail

ALLOW_WEAK_NEGATIVE_WEIGHTS

WEIGHT_TOLERANCE

TOLERANCE

label

type

logicType

outputText

bias

biasDelta

biasSum

biasSumDelta

posDirSum

negDirSum

negRecSum

posRecSum

posPassiveSum

requiredSum

metaBias

isMeta

numDisjunctiveSynapses

statistic

activationFunction

numberOfInputSynapses

outputRelations

inputSynapses

outputSynapses

passiveInputSynapses

outputNode

node

lock

passiveInputFunction

threads

BEGIN_COMP

END_COMP

Constructor Detail

INeuron

INeuron

INeuron

Method Detail

getThreadState

addInput

remove

propagate

getActivations

getActivation

clearActivations

clearActivations

clearActivations

compareTo

write

readFields

suspend

reactivate

setBias

changeBias

getNewBiasSum

register

update

readNeuron

isPassiveInputNeuron

registerPassiveInputSynapse

toString

toStringWithSynapses