NanoBrain.MemoryCell Class Reference

Description

A MemoryCell stored its value for one update.

When the input for a Memory Cell changes, it will output the previous value

Inheritance diagram for NanoBrain.MemoryCell:

Public Types
enum	CombinatorType { Sum , Product }
	The type of combinators. More...
enum	ActivationType {   Linear , Power , Sqrt , Reciprocal ,   Tanh , Binary , Normalized , Custom }
	The type of.
enum	Type { None , Neuron , MemoryCell , Cluster }
	The types of Nucleus.

Public Member Functions
	MemoryCell (Cluster parent, string name)
override Nucleus	ShallowCloneTo (Cluster newParent)
override void	UpdateStateIsolated ()
override void	UpdateNuclei ()
	Update the state and recursively all Nuclei receiving data from this Nucleus.
Synapse	AddSynapse (Neuron sendingNucleus, float weight=1)
	Add a new synapse to this nuclues.
Synapse	GetSynapse (Nucleus sender)
	Find a synapse.
void	RemoveSynapse (Nucleus sendingNucleus)
	Remove a synapse from a Nucleus.
virtual void	SetBias (Vector3 inputValue)
	Set the bias, recalculate the output and update all Nuclei receiving from this Nucleus.
AnimationCurve	GenerateCurve ()
void	SleepCheck ()
override Nucleus	Clone (ClusterPrefab prefab)
	Function to clone a nucleus to a Cluster prefab.
float3	CombinatorSum ()
Vector3	CombinatorSum ()
float3	CombinatorProduct ()
Vector3	CombinatorProduct ()
Vector3	CombinatorMax ()
virtual void	AddReceiver (Nucleus receiverToAdd, float weight=1)
virtual void	RemoveReceiver (Nucleus receiverToRemove)
virtual void	ProcessStimulus (Vector3 inputValue)
	Process an external stimulus.
virtual void	Initialize ()

Static Public Member Functions
static void	Delete (Nucleus nucleus)

Public Attributes
bool	staticMemory = false
Vector3	bias = Vector3.zero
	Create a new Neuron in a Cluster Prefab.
CombinatorType	combinator = CombinatorType.Sum
	The type of combinator used for this Neuron.
ActivationType	_curvePreset
AnimationCurve	curve
float	curveMax = 1.0f
Action	WhenFiring
bool	persistOutput = false
float	lastUpdate = 0
	Toggle for printing debugging trace data.
readonly float	timeToSleep = 1f
string	name
	The name of the Nucleus.
Cluster	parent
	The cluster prefab in which the nucleus is located.

Protected Member Functions
virtual void	CloneFields (Neuron clone)
void	CheckSleepingSynapses ()
float3	ActivatorLinear (float3 input)
Vector3	ActivatorLinear (Vector3 input)
float3	ActivatorSqrt (float3 input)
Vector3	ActivatorSqrt (Vector3 input)
float3	ActivatorPower (float3 input)
Vector3	ActivatorPower (Vector3 input)
float3	ActivatorReciprocal (float3 input)
Vector3	ActivatorReciprocal (Vector3 input)
float3	ActivatorTanh (float3 input)
float3	ActivatorBinary (float3 input)
float3	ActivatorNormalized (float3 input)
float3	ActivatorCustom (float3 input)
Vector3	ActivatorCustom (Vector3 input)

Protected Attributes
float3	_outputValue
Vector3	_outputValue

Properties
override bool	isSleeping [get]
List< Synapse >	synapses [get]
	The synapses of the nucleus.
ActivationType	curvePreset [get, set]
virtual float3	outputValue [get, set]
virtual Vector3	outputValue [get, set]
float	outputMagnitude [get]
float	outputSqrMagnitude [get]
bool	isFiring [get]
Func< float3 >	Combinator [get]
Func< Vector3 >	Combinator [get]
Func< float3, float3 >	Activator [get]
Func< Vector3, Vector3 >	Activator [get]
virtual List< Nucleus >	receivers [get, set]

Member Enumeration Documentation

CombinatorType

enum NanoBrain.Neuron.CombinatorType

inherited

The type of combinators.

A combinator combines the weighted values of the synapses to a single value

Enumerator
Sum	Add the weighted values together.
Product	Multiply the weighted values.

Member Function Documentation

UpdateNuclei()

override void NanoBrain.MemoryCell.UpdateNuclei ( )

virtual

Update the state and recursively all Nuclei receiving data from this Nucleus.

Reimplemented from NanoBrain.Nucleus.

AddSynapse()

Synapse NanoBrain.Neuron.AddSynapse ( Neuron  sendingNucleus, float  weight = 1  )

inherited

Add a new synapse to this nuclues.

Parameters

sendingNucleus	The nucleus from which the signals may originate
weight	The weight applied to the input. Default value = 1

Returns

The created Synapse

This will add a new input to this nucleus with the given weight.

GetSynapse()

Synapse NanoBrain.Neuron.GetSynapse ( Nucleus  sender )

inherited

Find a synapse.

Parameters

sender

The sender of the input to the Synapse

Returns

The found Synapse or null when the sender has no synapse to this nucleus.

RemoveSynapse()

void NanoBrain.Neuron.RemoveSynapse ( Nucleus  sendingNucleus )

inherited

Remove a synapse from a Nucleus.

Parameters

sendingNucleus

Remote the synapse connecting to this Nucleus

SetBias()

virtual void NanoBrain.Neuron.SetBias ( Vector3  inputValue )

virtualinherited

Set the bias, recalculate the output and update all Nuclei receiving from this Nucleus.

Parameters

inputValue

Clone()

override Nucleus NanoBrain.Neuron.Clone ( ClusterPrefab  prefab )

inherited

Function to clone a nucleus to a Cluster prefab.

Parameters

prefab

Returns

ProcessStimulus()

virtual void NanoBrain.Neuron.ProcessStimulus ( Vector3  inputValue )

virtualinherited

Process an external stimulus.

Parameters

inputValue	The value of the stimulus
thingId	The id of the thing causing the stimulus
thingName	The name of the thing causing the stimulus

Member Data Documentation

bias

Vector3 NanoBrain.Neuron.bias = Vector3.zero

inherited

Create a new Neuron in a Cluster Prefab.

Parameters

prefab	The Cluster Preafb in which the new Neuron should be created
name	The name of the new Neuron

The bias

The bias which a value which is always added to the combined value of the neuron It does not have a synapse and therefore no weight of source nucleus

parent

Cluster NanoBrain.Nucleus.parent

inherited

The cluster prefab in which the nucleus is located.

The cluster instance in which the nucleus is located

---

The documentation for this class was generated from the following file:

• /home/pascal/Development/Projects/Passer/NanoBrain/NanoBrain/Assets/NanoBrain-unitypackage/Runtime/Scripts/Core/MemoryCell.cs