Neuron (aika 0.6 API)

java.lang.Object
- org.aika.neuron.Neuron

All Implemented Interfaces:

Comparable<Neuron>, Writable

Direct Known Subclasses:

InputNeuron
```
public class Neuron
extends Object
implements Comparable<Neuron>, Writable
```
Author:

Lukas Molzberger

Nested Class Summary

Nested Classes
Modifier and Type Class and Description

static class Neuron.NormWeight

Nested Classes
Modifier and Type	Class and Description
`static class`	`Neuron.NormWeight`

Field Summary

Fields
Modifier and Type	Field and Description
`double`	`activationSum`
`double`	`bias`
`static AtomicInteger`	`currentNeuronId`
`int`	`id`
`boolean`	`initialized`
`TreeSet<Synapse>`	`inputSynapses`
`TreeSet<Synapse>`	`inputSynapsesByWeight`
`boolean`	`isBlocked`
`String`	`label`
`static double`	`LEARN_RATE`
`ReadWriteLock`	`lock`
`Model`	`m`
`static int`	`MAX_SELF_REFERENCING_DEPTH`
`double`	`maxRecurrentSum`
`double`	`negDirSum`
`double`	`negRecSum`
`Node`	`node`
`boolean`	`noTraining`
`int`	`numberOfActivations`
`TreeMap<Synapse.Key,InputNode>`	`outputNodes`
`TreeSet<Synapse>`	`outputSynapses`
`double`	`posRecSum`
`static double`	`TOLERANCE`
`static double`	`WEIGHT_TOLERANCE`

Constructor Summary

Constructors
Constructor and Description

Neuron()

Neuron(String label)

Neuron(String label, boolean isBlocked, boolean noTraining)

Constructors
Constructor and Description
`Neuron()`
`Neuron(String label)`
`Neuron(String label, boolean isBlocked, boolean noTraining)`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`double`	`avgActivation()`
`int`	`compareTo(Neuron n)`
`void`	`computeBounds(Activation act)`
`void`	`computeErrorSignal(Iteration t, Activation act)`
`Activation.State`	`computeWeight(int round, Activation act, ExpandNode en)`
`void`	`count(Iteration t)`
`static Neuron`	`create(Iteration t, Neuron n, double bias, double negDirSum, double negRecSum, double posRecSum, Set<Synapse> inputs)`
`void`	`propagateAddedActivation(Iteration t, Activation act)`
`void`	`propagateRemovedActivation(Iteration t, Activation act)`
`void`	`publish(Iteration t)`
`static Neuron`	`read(DataInput in, Iteration t)`
`void`	`readFields(DataInput in, Iteration t)` Deserialize the fields of this object from `in`.
`void`	`remove(Iteration t)`
`static double`	`sigmoid(double x)`
`String`	`toString()`
`String`	`toStringWithSynapses()`
`void`	`train(Iteration t, Activation act)`
`void`	`train(Iteration t, Activation iAct, Integer rid, double x, long v)`
`static double`	`transferFunction(double x)`
`void`	`unpublish(Iteration t)`
`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

LEARN_RATE
```
public static final double LEARN_RATE
```
See Also:

Constant Field Values

WEIGHT_TOLERANCE
```
public static final double WEIGHT_TOLERANCE
```
See Also:

Constant Field Values

TOLERANCE
```
public static final double TOLERANCE
```
See Also:

Constant Field Values

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

Constant Field Values

m
```
public Model m
```

currentNeuronId

public static AtomicInteger currentNeuronId

id
```
public int id
```

label
```
public String label
```

bias
```
public volatile double bias
```

negDirSum
```
public volatile double negDirSum
```

negRecSum
```
public volatile double negRecSum
```

posRecSum
```
public volatile double posRecSum
```

maxRecurrentSum
```
public volatile double maxRecurrentSum
```

outputSynapses
```
public TreeSet<Synapse> outputSynapses
```

inputSynapses
```
public TreeSet<Synapse> inputSynapses
```

inputSynapsesByWeight

public TreeSet<Synapse> inputSynapsesByWeight

outputNodes

public TreeMap<Synapse.Key,InputNode> outputNodes

node
```
public Node node
```

initialized
```
public boolean initialized
```

isBlocked
```
public boolean isBlocked
```

noTraining
```
public boolean noTraining
```

activationSum
```
public volatile double activationSum
```

numberOfActivations

public volatile int numberOfActivations

lock
```
public ReadWriteLock lock
```

Constructor Detail

Neuron
```
public Neuron()
```

Neuron
```
public Neuron(String label)
```

Neuron

public Neuron(String label,
              boolean isBlocked,
              boolean noTraining)

Method Detail

avgActivation
```
public double avgActivation()
```

create

public static Neuron create(Iteration t,
                            Neuron n,
                            double bias,
                            double negDirSum,
                            double negRecSum,
                            double posRecSum,
                            Set<Synapse> inputs)

publish
```
public void publish(Iteration t)
```

unpublish
```
public void unpublish(Iteration t)
```

remove
```
public void remove(Iteration t)
```

propagateAddedActivation

public void propagateAddedActivation(Iteration t,
                                     Activation act)

propagateRemovedActivation

public void propagateRemovedActivation(Iteration t,
                                       Activation act)

computeBounds

public void computeBounds(Activation act)

computeWeight

public Activation.State computeWeight(int round,
                                      Activation act,
                                      ExpandNode en)

computeErrorSignal

public void computeErrorSignal(Iteration t,
                               Activation act)

train

public void train(Iteration t,
                  Activation act)

train

public void train(Iteration t,
                  Activation iAct,
                  Integer rid,
                  double x,
                  long v)

transferFunction

public static double transferFunction(double x)

sigmoid

public static double sigmoid(double x)

count
```
public void count(Iteration t)
```

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,
                       Iteration t)
                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 Neuron read(DataInput in,
                          Iteration t)
                   throws IOException

Throws:: IOException

compareTo
```
public int compareTo(Neuron n)
```
Specified by:

compareTo in interface Comparable<Neuron>

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

toString in class Object

toStringWithSynapses
```
public String toStringWithSynapses()
```

Class Neuron

Nested Class Summary

Field Summary

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Field Detail

LEARN_RATE

WEIGHT_TOLERANCE

TOLERANCE

MAX_SELF_REFERENCING_DEPTH

m

currentNeuronId

id

label

bias

negDirSum

negRecSum

posRecSum

maxRecurrentSum

outputSynapses

inputSynapses

inputSynapsesByWeight

outputNodes

node

initialized

isBlocked

noTraining

activationSum

numberOfActivations

lock

Constructor Detail

Neuron

Neuron

Neuron

Method Detail

avgActivation

create

publish

unpublish

remove

propagateAddedActivation

propagateRemovedActivation

computeBounds

computeWeight

computeErrorSignal

train

train

transferFunction

sigmoid

count

write

readFields

read

compareTo

toString

toStringWithSynapses