org.aika

Class Model

java.lang.Object

org.aika.Model

All Implemented Interfaces:

Writable

public class Model
extends Object
implements Writable

The model consists of two layers. The first layer is the actual neural network consisting of neurons and synapses. The second layer is a pattern lattice containing a boolean logic representation of all the neurons. Whenever the synapse weights of a neuron are adjusted, then the underlying boolean logic representation of this neuron will be updated too. The model supports parallel processing using a fixed number of threads.

Author:

Lukas Molzberger

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Model.Statistic

Field Summary

Fields

Modifier and Type	Field and Description
Set<Node>[]	allNodes
Document[]	docs
int[]	documentCounter
Map<Integer,Node>	initialNodes
Map<String,Neuron>	labeledNeurons
int[]	lastCleanup
Map<Integer,Neuron>	neurons
int	numberOfPositions
Set<AndNode>	numberOfPositionsQueue
int	numberOfThreads
Model.Statistic	stat

Constructor Summary

Constructors

Constructor and Description
Model() Creates a model with a single thread.
Model(int numberOfThreads)

Method Summary

Modifier and Type	Method and Description
Neuron	createAndNeuron(Neuron n, double threshold, Collection<Input> inputs) Creates a neuron representing a conjunction of its inputs.
Neuron	createAndNeuron(Neuron n, double threshold, Input... inputs) Creates a neuron representing a conjunction of its inputs.
Neuron	createCounterNeuron(Neuron n, Neuron clockSignal, boolean dirCS, Neuron startSignal, boolean dirSS, boolean direction) A counter neuron is used to compute the relational id.
Document	createDocument(String txt)
Document	createDocument(String txt, int threadId)
Neuron	createNeuron(Neuron n, double bias, Collection<Input> inputs) Creates a neuron with the given bias.
Neuron	createNeuron(Neuron n, double bias, Input... inputs) Creates a neuron with the given bias.
InputNeuron	createOrLookupInputNeuron(String label) Creates an InputNeuron with the given label.
InputNeuron	createOrLookupInputNeuron(String label, boolean isBlocked)
Neuron	createOrNeuron(Neuron n, Input... inputs) Creates a neuron representing a disjunction of its inputs.
Neuron	createOrNeuron(Neuron n, Set<Input> inputs) Creates a neuron representing a disjunction of its inputs.
Neuron	createRelationalNeuron(Neuron n, Neuron ctn, Neuron inputSignal, boolean dirIS) A relational neuron combines the relational id created by a counter neuron with an input signal.
String	networkWeightsToString(boolean all)
static Model	read(DataInput in)
void	readFields(DataInput in, Document doc) Deserialize the fields of this object from in.
void	reset()
void	resetFrequency()
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

numberOfThreads

public int numberOfThreads

lastCleanup

public int[] lastCleanup

documentCounter

public int[] documentCounter

docs

public Document[] docs

labeledNeurons

public Map<String,Neuron> labeledNeurons

neurons

public Map<Integer,Neuron> neurons

initialNodes

public Map<Integer,Node> initialNodes

allNodes

public Set<Node>[] allNodes

stat

public Model.Statistic stat

numberOfPositionsQueue

public Set<AndNode> numberOfPositionsQueue

numberOfPositions

public volatile int numberOfPositions

Constructor Detail

Model

public Model()

Creates a model with a single thread.

Model

public Model(int numberOfThreads)

Method Detail

createDocument

public Document createDocument(String txt)

createDocument

public Document createDocument(String txt,
                               int threadId)

toString

public String toString()

Overrides:

toString in class Object

reset

public void reset()

resetFrequency

public void resetFrequency()

networkWeightsToString

public String networkWeightsToString(boolean all)

createOrLookupInputNeuron

public InputNeuron createOrLookupInputNeuron(String label)

Creates an InputNeuron with the given label.

Parameters:

label -

Returns:

createOrLookupInputNeuron

public InputNeuron createOrLookupInputNeuron(String label,
                                             boolean isBlocked)

createAndNeuron

public Neuron createAndNeuron(Neuron n,
                              double threshold,
                              Input... inputs)

Creates a neuron representing a conjunction of its inputs. This is just a convenience method to automatically compute the bias.

Parameters:

n -

threshold - A value between 0 and 1, determining how sensitive the resulting neuron will be.

inputs -

Returns:

createAndNeuron

public Neuron createAndNeuron(Neuron n,
                              double threshold,
                              Collection<Input> inputs)

Creates a neuron representing a conjunction of its inputs. This is just a convenience method to automatically compute the bias.

Parameters:

n -

threshold - A value between 0 and 1, determining how sensitive the resulting neuron will be.

inputs -

Returns:

createNeuron

public Neuron createNeuron(Neuron n,
                           double bias,
                           Input... inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

createNeuron

public Neuron createNeuron(Neuron n,
                           double bias,
                           Collection<Input> inputs)

Creates a neuron with the given bias.

Parameters:

n -

bias -

inputs -

Returns:

createOrNeuron

public Neuron createOrNeuron(Neuron n,
                             Input... inputs)

Creates a neuron representing a disjunction of its inputs. This is just a convenience method to automatically compute the bias.

Parameters:

n -

inputs -

Returns:

createOrNeuron

public Neuron createOrNeuron(Neuron n,
                             Set<Input> inputs)

Creates a neuron representing a disjunction of its inputs. This is just a convenience method to automatically compute the bias.

Parameters:

n -

inputs -

Returns:

createRelationalNeuron

public Neuron createRelationalNeuron(Neuron n,
                                     Neuron ctn,
                                     Neuron inputSignal,
                                     boolean dirIS)

A relational neuron combines the relational id created by a counter neuron with an input signal.

Parameters:

n -

ctn -

inputSignal -

dirIS -

Returns:

createCounterNeuron

public Neuron createCounterNeuron(Neuron n,
                                  Neuron clockSignal,
                                  boolean dirCS,
                                  Neuron startSignal,
                                  boolean dirSS,
                                  boolean direction)

A counter neuron is used to compute the relational id. It simply adds a new activation after each clock signal and increases the relational id by one.

Parameters:

n -

clockSignal -

dirCS - The direction of the clock signal.

startSignal -

dirSS - The direction of the start signal.

direction -

Returns:

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 Model read(DataInput in)
                  throws IOException

Throws:

IOException