ITK  4.0.0
Insight Segmentation and Registration Toolkit
Public Types | Public Member Functions | Static Public Member Functions | Protected Member Functions | Protected Attributes
itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector > Class Template Reference

The QuickPropLearningRule is the base class for all the ErrorBackPropagationLearning strategies. More...

#include <itkQuickPropLearningRule.h>

Inheritance diagram for itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >:
Collaboration diagram for itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >:

List of all members.

Public Types

typedef SmartPointer< const SelfConstPointer
typedef SmartPointer< SelfPointer
typedef QuickPropLearningRule Self
typedef LearningFunctionBase
< LayerType, TTargetVector > 
Superclass
typedef Superclass::ValueType ValueType

Public Member Functions

virtual ::itk::LightObject::Pointer CreateAnother (void) const
virtual const ValueTypeGetDecay ()
virtual const ValueTypeGetMax_Growth_Factor ()
virtual const char * GetNameOfClass () const
virtual void Learn (LayerType *layer, TTargetVector errors, ValueType learningrate)
virtual void Learn (LayerType *layer, ValueType learningrate)
virtual void SetDecay (ValueType _arg)
virtual void SetMax_Growth_Factor (ValueType _arg)

Static Public Member Functions

static Pointer New ()

Protected Member Functions

virtual void PrintSelf (std::ostream &os, Indent indent) const
 QuickPropLearningRule ()
virtual ~QuickPropLearningRule ()

Protected Attributes

ValueType m_Decay
ValueType m_Epsilon
ValueType m_Max_Growth_Factor
ValueType m_Momentum
ValueType m_SigmoidPrimeOffset
ValueType m_SplitEpsilon
ValueType m_Threshold

Detailed Description

template<class LayerType, class TTargetVector>
class itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >

The QuickPropLearningRule is the base class for all the ErrorBackPropagationLearning strategies.

ErrorBackPropagationLearning strategies include error back propagation, bp+momentum, conjugte gradient descent, and quick prop.

This class specifies how the errors are backpropagated for a layer. They take a LayerBase object as input and compute the input for the layers input weightset.

Definition at line 43 of file itkQuickPropLearningRule.h.


Member Typedef Documentation

template<class LayerType , class TTargetVector >
typedef SmartPointer<const Self> itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::ConstPointer
template<class LayerType , class TTargetVector >
typedef SmartPointer<Self> itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::Pointer
template<class LayerType , class TTargetVector >
typedef QuickPropLearningRule itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::Self

Standard class typedefs.

Reimplemented from itk::Statistics::LearningFunctionBase< LayerType, TTargetVector >.

Definition at line 47 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
typedef LearningFunctionBase<LayerType, TTargetVector> itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::Superclass
template<class LayerType , class TTargetVector >
typedef Superclass::ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::ValueType

Constructor & Destructor Documentation

template<class LayerType , class TTargetVector >
itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::QuickPropLearningRule ( ) [protected]
template<class LayerType , class TTargetVector >
virtual itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::~QuickPropLearningRule ( ) [inline, protected, virtual]

Definition at line 70 of file itkQuickPropLearningRule.h.


Member Function Documentation

template<class LayerType , class TTargetVector >
virtual::itk::LightObject::Pointer itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::CreateAnother ( void  ) const [virtual]

Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class.

Reimplemented from itk::LightProcessObject.

template<class LayerType , class TTargetVector >
virtual const ValueType& itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::GetDecay ( ) [virtual]
template<class LayerType , class TTargetVector >
virtual const ValueType& itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::GetMax_Growth_Factor ( ) [virtual]
template<class LayerType , class TTargetVector >
virtual const char* itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::GetNameOfClass ( ) const [virtual]

Method for creation through the object factory.

Reimplemented from itk::Statistics::LearningFunctionBase< LayerType, TTargetVector >.

template<class LayerType , class TTargetVector >
virtual void itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::Learn ( LayerType *  layer,
ValueType  learningrate 
) [virtual]
template<class LayerType , class TTargetVector >
virtual void itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::Learn ( LayerType *  layer,
TTargetVector  errors,
ValueType  learningrate 
) [virtual]
template<class LayerType , class TTargetVector >
static Pointer itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::New ( ) [static]

Method for creation through the object factory.

Reimplemented from itk::LightProcessObject.

template<class LayerType , class TTargetVector >
virtual void itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::PrintSelf ( std::ostream &  os,
Indent  indent 
) const [protected, virtual]

Method to print the object.

Reimplemented from itk::Statistics::LearningFunctionBase< LayerType, TTargetVector >.

template<class LayerType , class TTargetVector >
virtual void itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::SetDecay ( ValueType  _arg) [virtual]
template<class LayerType , class TTargetVector >
virtual void itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::SetMax_Growth_Factor ( ValueType  _arg) [virtual]

Member Data Documentation

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_Decay [protected]

Definition at line 74 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_Epsilon [protected]

Definition at line 76 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_Max_Growth_Factor [protected]

Definition at line 73 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_Momentum [protected]

Definition at line 70 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_SigmoidPrimeOffset [protected]

Definition at line 77 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_SplitEpsilon [protected]

Definition at line 78 of file itkQuickPropLearningRule.h.

template<class LayerType , class TTargetVector >
ValueType itk::Statistics::QuickPropLearningRule< LayerType, TTargetVector >::m_Threshold [protected]

Definition at line 75 of file itkQuickPropLearningRule.h.


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