INeuron (aika 0.14 API)

java.lang.Object
- org.aika.AbstractNode<Neuron,Activation>
- - org.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.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`
`String`	`activationFunctionKey`
`static boolean`	`ALLOW_WEAK_NEGATIVE_WEIGHTS`
`double`	`bias`
`double`	`biasDelta`
`double`	`biasSum`
`double`	`biasSumDelta`
`TreeMap<Synapse,Synapse>`	`inputSynapses`
`String`	`label`
`ReadWriteLock`	`lock`
`double`	`maxRecurrentSum`
`double`	`metaBias`
`double`	`negDirSum`
`double`	`negRecSum`
`Provider<OrNode>`	`node`
`TreeMap<Synapse.Key,Provider<InputNode>>`	`outputNodes`
`TreeMap<Synapse,Synapse>`	`outputSynapses`
`String`	`outputText`
`double`	`posDirSum`
`double`	`posRecSum`
`Writable`	`statistic`
`INeuron.ThreadState[]`	`threads`
`static double`	`TOLERANCE`
`INeuron.Type`	`type`
`static double`	`WEIGHT_TOLERANCE`

Fields inherited from class org.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)`
`Collection<Activation>`	`getActivations(Document doc)`
`Stream<Activation>`	`getActivationsStream(Document doc)`
`Collection<Activation>`	`getAllActivations(Document doc)`
`Collection<Activation>`	`getFinalActivations(Document doc)`
`Stream<Activation>`	`getFinalActivationsStream(Document doc)` `getFinalActivations` is a convenience method to retrieve all activations of the given neuron that are part of the final interpretation.
`Activation`	`getFirstActivation(Document doc)`
`double`	`getNewBiasSum()`
`INeuron.ThreadState`	`getThreadState(int threadId, boolean create)`
`void`	`linkActivation(Activation act)` Sets the incoming and outgoing links between neuron activations.
`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`	`remove()`
`void`	`setBias(double b)`
`void`	`suspend()`
`String`	`toString()`
`String`	`toStringWithSynapses()`
`static boolean`	`update(Model m, int threadId, Document doc, Neuron pn, double biasDelta, Collection<Synapse> modifiedSynapses)`
`void`	`write(DataOutput out)` Serialize the fields of this object to `out`.

Methods inherited from class org.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
```

outputText
```
public String outputText
```

bias
```
public volatile double bias
```

biasDelta
```
public volatile double biasDelta
```

biasSum
```
public volatile double biasSum
```

biasSumDelta
```
public volatile double biasSumDelta
```

metaBias
```
public volatile double metaBias
```

posDirSum
```
public volatile double posDirSum
```

negDirSum
```
public volatile double negDirSum
```

negRecSum
```
public volatile double negRecSum
```

posRecSum
```
public volatile double posRecSum
```

maxRecurrentSum
```
public volatile double maxRecurrentSum
```

statistic
```
public Writable statistic
```

activationFunction

public ActivationFunction activationFunction

activationFunctionKey
```
public String activationFunctionKey
```

inputSynapses

public TreeMap<Synapse,Synapse> inputSynapses

outputSynapses

public TreeMap<Synapse,Synapse> outputSynapses

outputNodes

public TreeMap<Synapse.Key,Provider<InputNode>> outputNodes

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

lock
```
public ReadWriteLock lock
```

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

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>

linkActivation
```
public void linkActivation(Activation act)
```
Sets the incoming and outgoing links between neuron activations.

Parameters:

act -

getActivations

public Collection<Activation> getActivations(Document doc)

getFirstActivation

public Activation getFirstActivation(Document doc)

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(Model m,
                             int threadId,
                             Document doc,
                             Neuron pn,
                             double biasDelta,
                             Collection<Synapse> modifiedSynapses)

readNeuron

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

Throws:: IOException

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

toString in class Object

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

getFinalActivationsStream
```
public Stream<Activation> getFinalActivationsStream(Document doc)
```
getFinalActivations is a convenience method to retrieve all activations of the given neuron that are part of the final interpretation. Before calling this method, the doc.process() needs to be called first.

Parameters:

doc - The current document

Returns:

A collection with all final activations of this neuron.

getActivationsStream

public Stream<Activation> getActivationsStream(Document doc)

getFinalActivations

public Collection<Activation> getFinalActivations(Document doc)

getAllActivations

public Collection<Activation> getAllActivations(Document doc)

Class INeuron

Nested Class Summary

Field Summary

Fields inherited from class org.aika.AbstractNode

Constructor Summary

Method Summary

Methods inherited from class org.aika.AbstractNode

Methods inherited from class java.lang.Object

Field Detail

ALLOW_WEAK_NEGATIVE_WEIGHTS

WEIGHT_TOLERANCE

TOLERANCE

label

type

outputText

bias

biasDelta

biasSum

biasSumDelta

metaBias

posDirSum

negDirSum

negRecSum

posRecSum

maxRecurrentSum

statistic

activationFunction

activationFunctionKey

inputSynapses

outputSynapses

outputNodes

node

lock

threads

Constructor Detail

INeuron

INeuron

INeuron

Method Detail

getThreadState

addInput

remove

propagate

linkActivation

getActivations

getFirstActivation

clearActivations

clearActivations

clearActivations

compareTo

write

readFields

suspend

reactivate

setBias

changeBias

getNewBiasSum

register

update

readNeuron

toString

toStringWithSynapses

getFinalActivationsStream

getActivationsStream

getFinalActivations

getAllActivations