Package network.aika.neuron

Class Synapse.Builder

java.lang.Object

network.aika.neuron.Synapse.Builder

All Implemented Interfaces:

Neuron.Builder

Enclosing class:

Synapse

public static class Synapse.Builder
extends java.lang.Object
implements Neuron.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	Description
double	bias
DistanceFunction	distanceFunction
boolean	identity
double	limit
Neuron	neuron
boolean	recurrent
java.lang.Integer	synapseId
double	weight

Constructor Summary

Constructors

Constructor	Description
Builder()

Method Summary

Modifier and Type	Method	Description
Synapse	getSynapse(Neuron outputNeuron)
void	registerSynapseIds(Neuron n)
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	setLimit(double limit)
Synapse.Builder	setNeuron(Neuron neuron)	Determines the input neuron.
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

recurrent

public boolean recurrent

neuron

public Neuron neuron

weight

public double weight

bias

public double bias

limit

public double limit

distanceFunction

public DistanceFunction distanceFunction

identity

public boolean identity

synapseId

public java.lang.Integer synapseId

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:

setLimit

public Synapse.Builder setLimit(double limit)

setDistanceFunction

public Synapse.Builder setDistanceFunction(DistanceFunction distFunc)

setIdentity

public Synapse.Builder setIdentity(boolean identity)

setSynapseId

public Synapse.Builder setSynapseId(int synapseId)

registerSynapseIds

public void registerSynapseIds(Neuron n)

Specified by:

registerSynapseIds in interface Neuron.Builder

getSynapse

public Synapse getSynapse(Neuron outputNeuron)