Synapse (aika 0.24 API)

java.lang.Object
- network.aika.neuron.Synapse

All Implemented Interfaces:

Writable
```
public class Synapse
extends Object
implements Writable
```
The Synapse class connects two neurons with each other. When propagating an activation signal, the weight of the synapse is multiplied with the activation value of the input neurons activation. The result is then added to the output neurons weighted sum to compute the output activation value. In contrast to a conventional neural network synapses in Aika do not just propagate the activation value from one neuron to the next, but also structural information like the text range and the relational id (e.g. word position) and also the interpretation to which the input activation belongs. To determine in which way the structural information should be propagated synapses in Aika possess a few more properties.
The properties relativeRid and absoluteRid determine either the relative difference between the rid of the input activation and the rid of the output activation or require a fixed rid as input.
The properties range match, range mapping and range output manipulate the ranges. The range match determines whether the input range begin or end is required to be equal, greater than or less than the range of the output activation. The range mapping can be used to map for example an input range end to an output range begin. Usually this simply maps begin to begin and end to end. The range output property is a boolean flag which determines whether the input range should be propagated to the output activation.
Furthermore, the property isRecurrent specifies if this synapse is a recurrent feedback link. Recurrent feedback links can be either negative or positive depending on the weight of the synapse. Recurrent feedback links kind of allow to use future information as inputs of a current neuron. Aika allows this by making assumptions about the recurrent input neuron. The class SearchNode modifies these assumptions until the best interpretation for this document is found.

Author:

Lukas Molzberger

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`Synapse.Builder` The `Builder` class is just a helper class which is used to initialize a neuron.
`static class`	`Synapse.State`

Field Summary

Fields
Modifier and Type	Field and Description
`double`	`bias`
`double`	`biasDelta`
`int`	`committedInDoc`
`static double`	`CONJUNCTION_THRESHOLD`
`int`	`createdInDoc`
`static double`	`DISJUNCTION_THRESHOLD`
`DistanceFunction`	`distanceFunction`
`Writable`	`extension`
`Integer`	`id`
`boolean`	`identity`
`boolean`	`inactive`
`Neuron`	`input`
`static Comparator<Synapse>`	`INPUT_SYNAPSE_COMP`
`boolean`	`isConjunction`
`boolean`	`isDisjunction`
`boolean`	`isRecurrent`
`double`	`limit`
`double`	`limitDelta`
`Neuron`	`output`
`static int`	`OUTPUT`
`static Comparator<Synapse>`	`OUTPUT_SYNAPSE_COMP`
`Map<Integer,Relation>`	`relations`
`boolean`	`toBeDeleted`
`static int`	`VARIABLE`
`double`	`weight` The weight of this synapse.
`double`	`weightDelta` The weight delta of this synapse.

Constructor Summary

Constructors
Constructor and Description

Synapse()

Synapse(Neuron input, Neuron output, Integer id)

Constructors
Constructor and Description
`Synapse()`
`Synapse(Neuron input, Neuron output, Integer id)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`static Synapse`	`createOrLookup(Document doc, Integer synapseId, Neuron inputNeuron, Neuron outputNeuron)`
`boolean`	`exists()`
`double`	`getMaxInputValue()`
`double`	`getNewBias()`
`double`	`getNewWeight()`
`Relation`	`getRelationById(Integer id)`
`boolean`	`isConjunction(Synapse.State state)`
`boolean`	`isDisjunction(Synapse.State state)`
`boolean`	`isNegative()`
`void`	`link()`
`boolean`	`linksAnyOutput()`
`Set<Integer>`	`linksOutput()`
`static Synapse`	`read(DataInput in, Model m)`
`void`	`readFields(DataInput in, Model m)` Deserialize the fields of this object from `in`.
`void`	`relink()`
`String`	`toString()`
`void`	`unlink()`
`void`	`update(Document doc, double weight, double bias, double limit)`
`void`	`updateDelta(Document doc, double weightDelta, double biasDelta, double limitDelta)`
`void`	`write(DataOutput out)` Serialize the fields of this object to `out`.

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

Field Detail

OUTPUT
```
public static final int OUTPUT
```
See Also:

Constant Field Values

VARIABLE
```
public static final int VARIABLE
```
See Also:

Constant Field Values

DISJUNCTION_THRESHOLD

public static double DISJUNCTION_THRESHOLD

CONJUNCTION_THRESHOLD

public static double CONJUNCTION_THRESHOLD

INPUT_SYNAPSE_COMP

public static final Comparator<Synapse> INPUT_SYNAPSE_COMP

OUTPUT_SYNAPSE_COMP

public static final Comparator<Synapse> OUTPUT_SYNAPSE_COMP

input
```
public Neuron input
```

output
```
public Neuron output
```

id
```
public Integer id
```

isRecurrent
```
public boolean isRecurrent
```

identity
```
public boolean identity
```

relations
```
public Map<Integer,Relation> relations
```

distanceFunction

public DistanceFunction distanceFunction

extension
```
public Writable extension
```

inactive
```
public boolean inactive
```

weight
```
public double weight
```
The weight of this synapse.

weightDelta
```
public double weightDelta
```
The weight delta of this synapse. The converter will use it to compute few internal parameters and then createOrLookup the weight variable.

bias
```
public double bias
```

biasDelta
```
public double biasDelta
```

limit
```
public double limit
```

limitDelta
```
public double limitDelta
```

toBeDeleted
```
public boolean toBeDeleted
```

isConjunction
```
public boolean isConjunction
```

isDisjunction
```
public boolean isDisjunction
```

createdInDoc
```
public int createdInDoc
```

committedInDoc
```
public int committedInDoc
```

Constructor Detail

Synapse
```
public Synapse()
```

Synapse

public Synapse(Neuron input,
               Neuron output,
               Integer id)

Method Detail

link
```
public void link()
```

relink
```
public void relink()
```

unlink
```
public void unlink()
```

getMaxInputValue
```
public double getMaxInputValue()
```

exists
```
public boolean exists()
```

isConjunction

public boolean isConjunction(Synapse.State state)

isDisjunction

public boolean isDisjunction(Synapse.State state)

updateDelta

public void updateDelta(Document doc,
                        double weightDelta,
                        double biasDelta,
                        double limitDelta)

update

public void update(Document doc,
                   double weight,
                   double bias,
                   double limit)

isNegative
```
public boolean isNegative()
```

getRelationById

public Relation getRelationById(Integer id)

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

toString in class Object

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

read

public static Synapse read(DataInput in,
                           Model m)
                    throws IOException

Throws:: IOException

createOrLookup

public static Synapse createOrLookup(Document doc,
                                     Integer synapseId,
                                     Neuron inputNeuron,
                                     Neuron outputNeuron)

getNewWeight
```
public double getNewWeight()
```

getNewBias
```
public double getNewBias()
```

linksOutput
```
public Set<Integer> linksOutput()
```

linksAnyOutput
```
public boolean linksAnyOutput()
```

Class Synapse

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

OUTPUT

VARIABLE

DISJUNCTION_THRESHOLD

CONJUNCTION_THRESHOLD

INPUT_SYNAPSE_COMP

OUTPUT_SYNAPSE_COMP

input

output

id

isRecurrent

identity

relations

distanceFunction

extension

inactive

weight

weightDelta

bias

biasDelta

limit

limitDelta

toBeDeleted

isConjunction

isDisjunction

createdInDoc

committedInDoc

Constructor Detail

Synapse

Synapse

Method Detail

link

relink

unlink

getMaxInputValue

exists

isConjunction

isDisjunction

updateDelta

update

isNegative

getRelationById

toString

write

readFields

read

createOrLookup

getNewWeight

getNewBias

linksOutput

linksAnyOutput