BiasedCluster Class Reference

In a BiasedCluster each neuron has an input, an output and a bias value. More...

Inheritance diagram for BiasedCluster:

Public Member Functions
	BiasedCluster (unsigned int numNeurons, QString name="unnamed")
	Construct a Cluster that contains numNeurons neurons.
	BiasedCluster (ConfigurationParameters &params, QString prefix)
	Constructor.
virtual	~BiasedCluster ()
	Destructor.
DoubleVector &	biases ()
	Get the array of biases, this returns the actual array not a copy.
const DoubleVector &	biases () const
	Get the array of biases, this returns the actual array not a copy.
double	getBias (unsigned int neuron)
	Get bias of the neuron.
void	randomize (double min, double max)
	Randomize the biases of BiasedCluster.
virtual void	save (ConfigurationParameters &params, QString prefix)
	Save the actual status of parameters into the ConfigurationParameters object passed.
void	setAllBiases (double bias)
	Set all biases with the same value.
void	setBias (unsigned int neuron, double bias)
	Set the bias of the neuron.
void	setBiases (const DoubleVector &biases)
	Set the biases from the vector given.
void	update ()
	Update the outputs of neurons.
Public Member Functions inherited from Cluster
	Cluster (unsigned int numNeurons, QString name="unnamed")
	Construct a Cluster.
	Cluster (ConfigurationParameters &params, QString prefix)
	Constructor.
virtual	~Cluster ()
	Destructor.
getStateVectorFuncPtr	getDelegateFor (QString stateVector)
	Return the pointer to function for retrieving the DoubleVector representing the state requested.
double	getInput (unsigned int neuron) const
	Get the input of neuron.
double	getOutput (unsigned int neuron) const
	Get the output of neuron.
DoubleVector &	inputs ()
	Get the array of inputs.
DoubleVector	inputs () const
	Get the array of inputs.
bool	isAccumulate () const
	return true if the Cluster will accumulates inputs
bool	needReset ()
	Return true if inputs needs a reset.
unsigned int	numNeurons () const
	Return the number of neurons (the length of input and output arrays)
OutputFunction *	outFunction () const
	Get the Output function.
DoubleVector &	outputs ()
	Get the array of outputs.
DoubleVector	outputs () const
	Get the array of outputs.
void	resetInputs ()
	Reset the inputs of this cluster; the inputs will be set to zero.
void	setAccumulate (bool mode)
	Enable/Disable accumulation mode If accumulation is enabled (true) then linkers attached to this Cluster will never resetInput and accumulates data, otherwise the inputs will be resetted at each step of neural network.
void	setAllInputs (double value)
	Set all the inputs with the same value Details...
void	setInput (unsigned int neuron, double value)
	Set the input of neuron Details...
void	setInputs (const DoubleVector &inputs)
	Set the inputs from the vector given.
void	setOutFunction (OutputFunction *up)
	Set the output function for all neurons contained This method create an internal copy of the OutputFunction passed
void	setOutput (unsigned int neuron, double value)
	Force the output of the neuron at value specified.
void	setOutputs (const DoubleVector &outputs)
	Set the outputs from the vector given.
Public Member Functions inherited from Updatable
	Updatable (QString name="unnamed")
	Constructor.
	Updatable (ConfigurationParameters &params, QString prefix)
	Constructor.
virtual	~Updatable ()
	Destructor.
QString	name () const
	Return its name.
void	setName (QString newname)
	Set the name of Updatable.
Public Member Functions inherited from ParameterSettableInConstructor
	ParameterSettableInConstructor (ConfigurationParameters &, QString)
void	addObserver (RuntimeParameterObserver *obs)
T	getRuntimeParameter (QString paramName)
virtual ParameterSettableUI *	getUIManager ()
	ParameterSettable ()
virtual void	postConfigureInitialization ()
void	removeObserver (RuntimeParameterObserver *obs)
void	setRuntimeParameter (QString paramName, T newvalue)
QString	typeName () const
Public Member Functions inherited from ParameterSettable
void	addObserver (RuntimeParameterObserver *obs)
T	getRuntimeParameter (QString paramName)
void	removeObserver (RuntimeParameterObserver *obs)
void	setRuntimeParameter (QString paramName, T newvalue)
QString	typeName () const

Static Public Member Functions
static void	describe (QString type)
	Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.
Static Public Member Functions inherited from Cluster
static void	describe (QString type)
	Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.
Static Public Member Functions inherited from Updatable
static void	describe (QString type)
	Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.
Static Public Member Functions inherited from ParameterSettableInConstructor
static void	describe (QString type)
static QString	fullParameterDescriptionPath (QString type, QString param)
static QString	fullSubgroupDescriptionPath (QString type, QString sub)
Static Public Member Functions inherited from ParameterSettable
static void	describe (QString type)
static QString	fullParameterDescriptionPath (QString type, QString param)
static QString	fullSubgroupDescriptionPath (QString type, QString sub)

Additional Inherited Members
Public Types inherited from Cluster
typedef DoubleVector &(*	getStateVectorFuncPtr )(Cluster *)
	Delegate type for retrieving a vector by name (pointer to function) It works in this way:
Public Attributes inherited from ParameterSettableInConstructor
	AllowMultiple
	Default
	IsList
	IsMandatory
Static Public Attributes inherited from ParameterSettableInConstructor
static const double	Infinity
static const int	MaxInteger
static const int	MinInteger
Protected Member Functions inherited from Cluster
template<class T , DoubleVector &(T::*)() TMethod>
void	setDelegateFor (QString vectorName)
	Configure a delegate for a specifing state vector; who implements subclasses of Cluster has to specify a name and the method used to retrieve any state vector that needs to be public (i.e.
void	setNeedReset (bool b)
	Set the state of 'needReset' Used by subclasses into update implementation.
Static Protected Member Functions inherited from ParameterSettableInConstructor
static Descriptor	addTypeDescription (QString type, QString shortHelp, QString longHelp=QString(""))
static void	setGraphicalEditor (QString type)
Protected Attributes inherited from Cluster
DoubleVector *	inputdataptr
	Pointer to data Input.
DoubleVector *	outputdataptr
	Pointer to data Output.

Detailed Description

In a BiasedCluster each neuron has an input, an output and a bias value.

Motivation

Description

All neurons in the Cluster have the same transfer function which is given to the constructor by the outfunction property (see API doc).

Warnings

Definition at line 44 of file biasedcluster.h.

Constructor & Destructor Documentation

BiasedCluster	(	unsigned int	numNeurons,
		QString	name = "unnamed"
	)

Construct a Cluster that contains numNeurons neurons.

Definition at line 27 of file biasedcluster.cpp.

References DoubleVector::zeroing().

BiasedCluster	(	ConfigurationParameters &	params,
		QString	prefix
	)

Constructor.

Definition at line 34 of file biasedcluster.cpp.

References DoubleVector::copyValues(), ConfigurationHelper::getVector(), and Cluster::numNeurons().

~BiasedCluster ( )

virtual

Destructor.

Definition at line 50 of file biasedcluster.cpp.

Member Function Documentation

DoubleVector& biases ( )

inline

Get the array of biases, this returns the actual array not a copy.

This allows you to change the biases using the pointer returned!

Definition at line 65 of file biasedcluster.h.

Referenced by BiasedCluster::update().

const DoubleVector& biases ( ) const

inline

Get the array of biases, this returns the actual array not a copy.

This allows you to change the biases using the pointer returned!

Definition at line 71 of file biasedcluster.h.

void describe ( QString  type )

static

Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.

Definition at line 94 of file biasedcluster.cpp.

References ParameterSettableInConstructor::addTypeDescription(), Cluster::describe(), ParameterSettable::Descriptor::describeReal(), ParameterSettable::RealDescriptor::help(), ParameterSettableInConstructor::IsList, and ParameterSettable::RealDescriptor::props().

double getBias

(

unsigned int

neuron

)

Get bias of the neuron.

Definition at line 72 of file biasedcluster.cpp.

void randomize ( double  min, double  max  )

virtual

Randomize the biases of BiasedCluster.

Implements Cluster.

Definition at line 76 of file biasedcluster.cpp.

References globalRNG, and Cluster::numNeurons().

void save ( ConfigurationParameters &  params, QString  prefix  )

virtual

Save the actual status of parameters into the ConfigurationParameters object passed.

Parameters

params	the configuration parameters object on which save actual parameters
prefix	the prefix to use to access the object configuration parameters.

Reimplemented from Cluster.

Definition at line 82 of file biasedcluster.cpp.

References ConfigurationParameters::createParameter(), Cluster::save(), DoubleVector::size(), and ConfigurationParameters::startObjectParameters().

void setAllBiases

(

double

bias

)

Set all biases with the same value.

Definition at line 64 of file biasedcluster.cpp.

References DoubleVector::setAll().

void setBias	(	unsigned int	neuron,
		double	bias
	)

Set the bias of the neuron.

Definition at line 60 of file biasedcluster.cpp.

void setBiases

(

const DoubleVector &

biases

)

Set the biases from the vector given.

Definition at line 68 of file biasedcluster.cpp.

References DoubleVector::copyValues().

void update ( )

virtual

Update the outputs of neurons.

Implements Updatable.

Definition at line 53 of file biasedcluster.cpp.

References OutputFunction::apply(), BiasedCluster::biases(), Cluster::inputs(), Cluster::outFunction(), Cluster::outputs(), Cluster::setNeedReset(), and farsa::subtract().

---

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

• nnfw/include/biasedcluster.h
• nnfw/src/biasedcluster.cpp