OutputFunction Class Reference

OutputFunction Class. More...

Inheritance diagram for OutputFunction:

Public Member Functions
	OutputFunction ()
	Constructor. More...
virtual	~OutputFunction ()
	Destructor. More...
virtual void	apply (DoubleVector &inputs, DoubleVector &outputs)=0
	Calculate the outputs of neurons by the net inputs given. More...
double	apply (double input)
	Calculate the outputs of a single neuron. More...
virtual bool	derivate (const DoubleVector &inputs, const DoubleVector &outputs, DoubleVector &derivates) const
	Compute the derivate of the function represent Given the input of neurons and the corresponding output of neurons, it calculate the derivate. More...
void	setCluster (Cluster *cl)
	Set the Cluster which it is inserted This is automatically called, and in normal case you don't have to call it directly. More...
Public Member Functions inherited from ParameterSettableWithConfigureFunction
virtual void	configure (ConfigurationParameters &params, QString prefix)=0
Public Member Functions inherited from ParameterSettable
void	addObserver (RuntimeParameterObserver *obs)
T	getRuntimeParameter (QString paramName)
virtual ParameterSettableUI *	getUIManager ()
virtual void	postConfigureInitialization ()
void	removeObserver (RuntimeParameterObserver *obs)
virtual void	save (ConfigurationParameters &params, QString prefix)=0
void	setRuntimeParameter (QString paramName, T newvalue)
QString	typeName () const

Protected Member Functions
virtual void	clusterSetted ()
	The method setCluster will call clusterSetted to inform subclasses that the OutputFunction has been inserted into a Cluster. More...
Protected Member Functions inherited from ParameterSettable
void	notifyChangesToParam (QString paramName)

Protected Attributes
Cluster *	clusterv
	Cluster on which the OutputFunction is inserted. More...

Additional Inherited Members
Public Types inherited from ParameterSettable
enum	Property
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)
Public Attributes inherited from ParameterSettable
	AllowMultiple
	Default
	IsList
	IsMandatory
Static Public Attributes inherited from ParameterSettable
static const double	Infinity
static const int	MaxInteger
static const int	MinInteger
Static Protected Member Functions inherited from ParameterSettable
static Descriptor	addTypeDescription (QString type, QString shortHelp, QString longHelp=QString(""))
static void	setGraphicalEditor (QString type)

Detailed Description

OutputFunction Class.

Details...

Definition at line 39 of file outputfunction.h.

Constructor & Destructor Documentation

OutputFunction ( )

inline

Constructor.

Definition at line 42 of file outputfunction.h.

virtual ~OutputFunction ( )

inlinevirtual

Destructor.

Definition at line 44 of file outputfunction.h.

Member Function Documentation

virtual void apply ( DoubleVector &  inputs, DoubleVector &  outputs  )

pure virtual

Calculate the outputs of neurons by the net inputs given.

Implemented in LinearComboFunction, CompositeFunction, LogLikeFunction, LeakyIntegratorFunction, StepFunction, LinearFunction, RampFunction, ScaledSigmoidFunction, FakeSigmoidFunction, PseudoGaussFunction, SigmoidFunction, SinFunction, GainFunction, TriangleFunction, SawtoothFunction, ScaleFunction, WinnerTakeAllFunction, GaussFunction, IdentityFunction, and PeriodicFunction.

Referenced by SimpleCluster::update(), and BiasedCluster::update().

double apply ( double  input )

inline

Calculate the outputs of a single neuron.

Definition at line 48 of file outputfunction.h.

virtual void clusterSetted ( )

inlineprotectedvirtual

The method setCluster will call clusterSetted to inform subclasses that the OutputFunction has been inserted into a Cluster.

Reimplemented in LinearComboFunction, CompositeFunction, and LeakyIntegratorFunction.

Definition at line 77 of file outputfunction.h.

virtual bool derivate ( const DoubleVector &  inputs, const DoubleVector &  outputs, DoubleVector &  derivates  ) const

inlinevirtual

Compute the derivate of the function represent
Given the input of neurons and the corresponding output of neurons, it calculate the derivate.

Returns

if it return false, then the OutputFunction is not derivable, and the derivates DoubleVector can contains trash data.

Reimplemented in StepFunction, LinearFunction, RampFunction, ScaledSigmoidFunction, FakeSigmoidFunction, SigmoidFunction, GainFunction, ScaleFunction, GaussFunction, and IdentityFunction.

Definition at line 59 of file outputfunction.h.

void setCluster ( Cluster *  cl )

inline

Set the Cluster which it is inserted
This is automatically called, and in normal case you don't have to call it directly.

Definition at line 68 of file outputfunction.h.

Member Data Documentation

Cluster* clusterv

protected

Cluster on which the OutputFunction is inserted.

Definition at line 77 of file outputfunction.h.

Referenced by LeakyIntegratorFunction::clusterSetted(), CompositeFunction::clusterSetted(), LinearComboFunction::clusterSetted(), CompositeFunction::setFirstFunction(), LinearComboFunction::setFirstFunction(), CompositeFunction::setSecondFunction(), and LinearComboFunction::setSecondFunction().

---

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

• nnfw/include/outputfunction.h