network.aika.neuron

Class Synapse.Builder

java.lang.Object

network.aika.neuron.Synapse.Builder

All Implemented Interfaces:

Comparable<Synapse.Builder>

Enclosing class:

Synapse

public static class Synapse.Builder
extends Object
implements Comparable<Synapse.Builder>

The Builder class is just a helper class which is used to initialize a neuron. Most of the parameters of this class will be mapped to a input synapse for this neuron.

Author:

Lukas Molzberger

Field Summary

Fields

Modifier and Type	Field and Description
double	bias
DistanceFunction	distanceFunction
boolean	identity
Neuron	neuron
static int	OUTPUT
int	rangeInput
Range.Output	rangeOutput
boolean	recurrent
Map<Integer,Relation>	relations
Integer	synapseId
double	weight

Constructor Summary

Constructors

Constructor and Description
Builder()

Method Summary

Modifier and Type	Method and Description
Synapse.Builder	addInstanceRelation(InstanceRelation.Type type, int synapseId)
Synapse.Builder	addRangeRelation(Range.Relation relation, int synapseId)
Synapse.Builder	addRelations(Map<Integer,Relation> relations)
int	compareTo(Synapse.Builder in)
Synapse	getSynapse(Neuron outputNeuron)
Synapse.Builder	setBias(double bias) The bias of this input that will later on be added to the neurons bias.
Synapse.Builder	setDistanceFunction(DistanceFunction distFunc)
Synapse.Builder	setIdentity(boolean identity)
Synapse.Builder	setNeuron(Neuron neuron) Determines the input neuron.
Synapse.Builder	setRangeInput(int synapseId) By default the output range of th synapses input neuron is used.
Synapse.Builder	setRangeOutput(boolean ro) setRangeOutput is just a convenience function to call setBeginRangeOutput and setEndRangeOutput at the same time.
Synapse.Builder	setRangeOutput(boolean begin, boolean end) setRangeOutput is just a convenience function to call setBeginRangeOutput and setEndRangeOutput at the same time.
Synapse.Builder	setRangeOutput(Range.Mapping begin, Range.Mapping end) Determines if this input is used to compute the range start of the output activation.
Synapse.Builder	setRangeOutput(Range.Output rangeOutput) setRangeOutput is just a convenience function to call setBeginRangeOutput and setEndRangeOutput at the same time.
Synapse.Builder	setRecurrent(boolean recurrent) The property recurrent specifies if input is a recurrent feedback link.
Synapse.Builder	setSynapseId(int synapseId)
Synapse.Builder	setWeight(double weight) The synapse weight of this input.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

OUTPUT

public static final int OUTPUT

See Also:

Constant Field Values

recurrent

public boolean recurrent

neuron

public Neuron neuron

weight

public double weight

bias

public double bias

distanceFunction

public DistanceFunction distanceFunction

rangeInput

public int rangeInput

rangeOutput

public Range.Output rangeOutput

identity

public boolean identity

synapseId

public Integer synapseId

relations

public Map<Integer,Relation> relations

Constructor Detail

Builder

public Builder()

Method Detail

setRecurrent

public Synapse.Builder setRecurrent(boolean recurrent)

The property recurrent specifies if input 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.

Parameters:

recurrent -

Returns:

setNeuron

public Synapse.Builder setNeuron(Neuron neuron)

Determines the input neuron.

Parameters:

neuron -

Returns:

setWeight

public Synapse.Builder setWeight(double weight)

The synapse weight of this input.

Parameters:

weight -

Returns:

setBias

public Synapse.Builder setBias(double bias)

The bias of this input that will later on be added to the neurons bias.

Parameters:

bias -

Returns:

setDistanceFunction

public Synapse.Builder setDistanceFunction(DistanceFunction distFunc)

setRangeInput

public Synapse.Builder setRangeInput(int synapseId)

By default the output range of th synapses input neuron is used. Using this setter a specific input synapse of the input neuron might be chosen as a source for the range.

Parameters:

synapseId -

Returns:

setRangeOutput

public Synapse.Builder setRangeOutput(boolean ro)

setRangeOutput is just a convenience function to call setBeginRangeOutput and setEndRangeOutput at the same time.

Parameters:

ro -

Returns:

setRangeOutput

public Synapse.Builder setRangeOutput(boolean begin,
                                      boolean end)

setRangeOutput is just a convenience function to call setBeginRangeOutput and setEndRangeOutput at the same time.

Parameters:

begin -

end -

Returns:

setIdentity

public Synapse.Builder setIdentity(boolean identity)

setRangeOutput

public Synapse.Builder setRangeOutput(Range.Output rangeOutput)

setRangeOutput is just a convenience function to call setBeginRangeOutput and setEndRangeOutput at the same time.

Parameters:

rangeOutput -

Returns:

setRangeOutput

public Synapse.Builder setRangeOutput(Range.Mapping begin,
                                      Range.Mapping end)

Determines if this input is used to compute the range start of the output activation.

Parameters:

begin -

end -

Returns:

setSynapseId

public Synapse.Builder setSynapseId(int synapseId)

addRelations

public Synapse.Builder addRelations(Map<Integer,Relation> relations)

addInstanceRelation

public Synapse.Builder addInstanceRelation(InstanceRelation.Type type,
                                           int synapseId)

addRangeRelation

public Synapse.Builder addRangeRelation(Range.Relation relation,
                                        int synapseId)

getSynapse

public Synapse getSynapse(Neuron outputNeuron)

compareTo

public int compareTo(Synapse.Builder in)

Specified by:

compareTo in interface Comparable<Synapse.Builder>