FakeCluster Class Reference

FakeCluster Class. The FakeCluster is a Cluster without neurons, it's like an array ! :-). More...

Inheritance diagram for FakeCluster:

[legend]Collaboration diagram for FakeCluster:


Constructors
	FakeCluster (u_int size, const char *name="unnamed")
	FakeCluster (PropertySettings &)
virtual	~FakeCluster ()
Interface
void	update ()
void	randomize (Real min, Real max)
virtual FakeCluster *	clone () const

Detailed Description

Description: The FakeCluster implemented the Cluster Interface so it can be inserted inside a BaseNeuralNet, but it doesn't contains neurons, but it contains a simple vector with values and inputs and outputs are alias name for this vector of data.
It's very useful for inputs layers that don't needs true neurons but only a vector where registry the sensors values.

Warnings: Due to fact that outputs() are simple an alias, or more precisly a VectorData view, of inputs(), this means that a call to resetInputs() method also resets the outputs!! In general, all methods that modify inputs also modify outputs and viceversa.

Name	Type [isVector]	Access mode	Description	Class
Properties
typename	string	read-only	Class's type	Propertized
name	string	read/write	name of the object	Updatable
accumulate	boolean	read/write	if inputs are accumulated	Cluster
inputs	RealVec	read/write	neuron's input	Cluster
outfunction	OutputFunction	read/write	ignored	Cluster
outputs	RealVec	read/write	neuron's output (same of inputs)	Cluster
size	unsigned int	read-only	number of neurons	Cluster

Construct a FakeCluster

FakeCluster ( PropertySettings & )

Construct by PropertySettings

virtual ~FakeCluster ( ) [virtual]

Destructor

void update ( ) [virtual]

Update ;-) It's do nothing !!

Implements Updatable.

Randomize ?!?! it do nothings

Implements Cluster.

virtual FakeCluster* clone ( ) const [virtual]

Reimplemented from Cluster.

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

Documentation generated by