org.aika.neuron

Class Synapse

java.lang.Object

org.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 in Aika synapses 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 posses 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.Key

Field Summary

Fields

Modifier and Type	Field and Description
Neuron	input
static Comparator<Synapse>	INPUT_SYNAPSE_BY_WEIGHTS_COMP
static Comparator<Synapse>	INPUT_SYNAPSE_COMP
InputNode	inputNode
Synapse.Key	key
double	maxLowerWeightsSum
Neuron	output
static Comparator<Synapse>	OUTPUT_SYNAPSE_COMP
double	w

Constructor Summary

Constructors

Constructor and Description
Synapse()
Synapse(Neuron input)
Synapse(Neuron input, Synapse.Key key)

Method Summary

Modifier and Type	Method and Description
static int	compareWeights(Double a, Double b, double tolerance)
void	link(Document doc)
static Synapse	read(DataInput in, Document doc)
void	readFields(DataInput in, Document doc) Deserialize the fields of this object from in.
String	toString()
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

INPUT_SYNAPSE_BY_WEIGHTS_COMP

public static final Comparator<Synapse> INPUT_SYNAPSE_BY_WEIGHTS_COMP

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

inputNode

public InputNode inputNode

key

public Synapse.Key key

w

public double w

maxLowerWeightsSum

public double maxLowerWeightsSum

Constructor Detail

Synapse

public Synapse()

Synapse

public Synapse(Neuron input)

Synapse

public Synapse(Neuron input,
               Synapse.Key key)

Method Detail

link

public void link(Document doc)

compareWeights

public static int compareWeights(Double a,
                                 Double b,
                                 double tolerance)

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,
                       Document doc)
                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,
                           Document doc)
                    throws IOException

Throws:

IOException