Main Page   Groups   Namespace List   Class Hierarchy   Alphabetical List   Compound List   File List   Namespace Members   Compound Members   File Members   Concepts

# itk::AmoebaOptimizer Class Reference [Numerics, Optimizers]

`#include <itkAmoebaOptimizer.h>`

Inheritance diagram for itk::AmoebaOptimizer:

[legend]
Collaboration diagram for itk::AmoebaOptimizer:

[legend]
List of all members.

## Detailed Description

Wrap of the vnl_amoeba algorithm.

AmoebaOptimizer is a wrapper around the vnl_amoeba algorithm which is an implementation of the Nelder-Meade downhill simplex problem. For most problems, it is a few times slower than a Levenberg-Marquardt algorithm but does not require derivatives of its cost function. It works by creating a simplex (n+1 points in ND space). The cost function is evaluated at each corner of the simplex. The simplex is then modified (by reflecting a corner about the opposite edge, by shrinking the entire simplex, by contracting one edge of the simplex, or by expanding the simplex) in searching for the minimum of the cost function.

The methods AutomaticInitialSimplex() and SetInitialSimplexDelta() control whether the optimizer defines the initial simplex automatically (by constructing a very small simplex around the initial position) or uses a user supplied simplex size.

AmoebaOptimizer can only minimize a function.

Definition at line 49 of file itkAmoebaOptimizer.h.

## Public Types

typedef ReceptorMemberCommand<
Self
CommandType
typedef SmartPointer< const
Self
ConstPointer
typedef CostFunctionType::Pointer CostFunctionPointer
typedef SingleValuedCostFunction CostFunctionType
typedef CostFunctionType::DerivativeType DerivativeType
typedef vnl_amoeba InternalOptimizerType
typedef vnl_vector< double > InternalParametersType
typedef CostFunctionType::MeasureType MeasureType
typedef Superclass::ParametersType ParametersType
typedef SmartPointer< SelfPointer
typedef Superclass::ScalesType ScalesType
typedef AmoebaOptimizer Self
typedef SingleValuedNonLinearVnlOptimizer Superclass

## Public Member Functions

virtual LightObject::Pointer CreateAnother () const
virtual void DebugOff () const
virtual void DebugOn () const
virtual void Delete ()
CommandGetCommand (unsigned long tag)
virtual const CostFunctionTypeGetCostFunction ()
virtual const ParametersTypeGetCurrentPosition ()
bool GetDebug () const
virtual const ParametersTypeGetInitialPosition ()
virtual unsigned long GetMTime () const
virtual const char * GetNameOfClass () const
vnl_amoeba * GetOptimizer (void)
virtual int GetReferenceCount () const
virtual const ScalesTypeGetScales ()
MeasureType GetValue (const ParametersType &parameters) const
MeasureType GetValue () const
bool HasObserver (const EventObject &event) const
void InvokeEvent (const EventObject &) const
void InvokeEvent (const EventObject &)
virtual void Modified () const
void Print (std::ostream &os, Indent indent=0) const
virtual void Register () const
void RemoveAllObservers ()
void RemoveObserver (unsigned long tag)
virtual void SetCostFunction (CostFunctionType *costFunction)
virtual void SetCostFunction (SingleValuedCostFunction *costFunction)
void SetDebug (bool debugFlag) const
virtual void SetInitialPosition (const ParametersType &param)
virtual void SetReferenceCount (int)
void SetScales (const ScalesType &scales)
void StartOptimization (void)
virtual void UnRegister () const
unsigned long AddObserver (const EventObject &event, Command *) const
unsigned long AddObserver (const EventObject &event, Command *)
virtual void AutomaticInitialSimplexOff ()
virtual void AutomaticInitialSimplexOn ()
virtual bool GetAutomaticInitialSimplex ()
virtual void SetAutomaticInitialSimplex (bool _arg)
virtual const ParametersTypeGetCachedCurrentPosition ()
virtual const DerivativeTypeGetCachedDerivative ()
virtual const MeasureTypeGetCachedValue ()
virtual double GetFunctionConvergenceTolerance ()
virtual double GetParametersConvergenceTolerance ()
virtual void SetFunctionConvergenceTolerance (double tol)
virtual void SetParametersConvergenceTolerance (double tol)
virtual ParametersType GetInitialSimplexDelta ()
virtual void SetInitialSimplexDelta (ParametersType _arg)
virtual const bool & GetMaximize ()
bool GetMinimize () const
virtual void MaximizeOff ()
virtual void MaximizeOn ()
void MinimizeOff ()
void MinimizeOn ()
virtual void SetMaximize (bool _arg)
void SetMinimize (bool v)
virtual unsigned int GetMaximumNumberOfIterations ()
virtual void SetMaximumNumberOfIterations (unsigned int n)

## Static Public Member Functions

static void BreakOnError ()
static Pointer New ()
static bool GetGlobalWarningDisplay ()
static void GlobalWarningDisplayOff ()
static void GlobalWarningDisplayOn ()
static void SetGlobalWarningDisplay (bool flag)

## Protected Types

typedef int InternalReferenceCountType

## Protected Member Functions

AmoebaOptimizer ()
bool PrintObservers (std::ostream &os, Indent indent) const
void PrintSelf (std::ostream &os, Indent indent) const
virtual void SetCurrentPosition (const ParametersType &param)
virtual ~AmoebaOptimizer ()
virtual void PrintHeader (std::ostream &os, Indent indent) const
virtual void PrintTrailer (std::ostream &os, Indent indent) const

## Protected Attributes

CostFunctionPointer m_CostFunction
ParametersType m_CurrentPosition
InternalReferenceCountType m_ReferenceCount
SimpleFastMutexLock m_ReferenceCountLock
bool m_ScalesInitialized

## Member Typedef Documentation

 typedef ReceptorMemberCommand< Self > itk::SingleValuedNonLinearVnlOptimizer::CommandType` [inherited]`

Command observer that will interact with the ITK-VNL cost-function adaptor in order to generate iteration events. This will allow to overcome the limitation of VNL optimizers not offering callbacks for every iteration

Definition at line 48 of file itkSingleValuedNonLinearVnlOptimizer.h.

 typedef SmartPointer itk::AmoebaOptimizer::ConstPointer

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

Definition at line 57 of file itkAmoebaOptimizer.h.

 typedef Superclass::CostFunctionAdaptorType itk::AmoebaOptimizer::CostFunctionAdaptorType` [protected]`

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

Definition at line 132 of file itkAmoebaOptimizer.h.

 typedef CostFunctionType::Pointer itk::SingleValuedNonLinearOptimizer::CostFunctionPointer` [inherited]`

Definition at line 56 of file itkSingleValuedNonLinearOptimizer.h.

 typedef SingleValuedCostFunction itk::SingleValuedNonLinearOptimizer::CostFunctionType` [inherited]`

Type of the Cost Function

Definition at line 55 of file itkSingleValuedNonLinearOptimizer.h.

 typedef CostFunctionType::DerivativeType itk::SingleValuedNonLinearOptimizer::DerivativeType` [inherited]`

Derivative type. It defines a type used to return the cost function derivative.

Definition at line 64 of file itkSingleValuedNonLinearOptimizer.h.

 typedef vnl_amoeba itk::AmoebaOptimizer::InternalOptimizerType

Internal optimizer type.

Definition at line 73 of file itkAmoebaOptimizer.h.

 typedef vnl_vector itk::AmoebaOptimizer::InternalParametersType

InternalParameters typedef.

Definition at line 70 of file itkAmoebaOptimizer.h.

 typedef int itk::LightObject::InternalReferenceCountType` [protected, inherited]`

Define the type of the reference count according to the target. This allows the use of atomic operations

Definition at line 139 of file itkLightObject.h.

 typedef CostFunctionType::MeasureType itk::SingleValuedNonLinearOptimizer::MeasureType` [inherited]`

Measure type. It defines a type used to return the cost function value.

Definition at line 60 of file itkSingleValuedNonLinearOptimizer.h.

Parameters type. It defines a position in the optimization search space.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 63 of file itkAmoebaOptimizer.h.

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

Definition at line 56 of file itkAmoebaOptimizer.h.

 typedef Superclass::ScalesType itk::NonLinearOptimizer::ScalesType` [inherited]`

Scale type. This array defines scale to be applied to parameters before being evaluated in the cost function. This allows to map to a more convenient space. In particular this is used to normalize parameter spaces in which some parameters have a different dynamic range.

Reimplemented from itk::Optimizer.

Definition at line 52 of file itkNonLinearOptimizer.h.

Standard "Self" typedef.

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

Definition at line 54 of file itkAmoebaOptimizer.h.

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

Definition at line 55 of file itkAmoebaOptimizer.h.

## Constructor & Destructor Documentation

 itk::AmoebaOptimizer::AmoebaOptimizer ( ) ` [protected]`

 virtual itk::AmoebaOptimizer::~AmoebaOptimizer ( ) ` [protected, virtual]`

## Member Function Documentation

 unsigned long itk::Object::AddObserver ( const EventObject & event, Command * ) const` [inherited]`

 unsigned long itk::Object::AddObserver ( const EventObject & event, Command * ) ` [inherited]`

Allow people to add/remove/invoke observers (callbacks) to any ITK object. This is an implementation of the subject/observer design pattern. An observer is added by specifying an event to respond to and an itk::Command to execute. It returns an unsigned long tag which can be used later to remove the event or retrieve the command. The memory for the Command becomes the responsibility of this object, so don't pass the same instance of a command to two different objects

 virtual void itk::AmoebaOptimizer::AutomaticInitialSimplexOff ( ) ` [virtual]`

 virtual void itk::AmoebaOptimizer::AutomaticInitialSimplexOn ( ) ` [virtual]`

 static void itk::LightObject::BreakOnError ( ) ` [static, inherited]`

This method is called when itkExceptionMacro executes. It allows the debugger to break on error.

 virtual LightObject::Pointer itk::Object::CreateAnother ( ) const` [virtual, inherited]`

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::LightObject.

 virtual void itk::Object::DebugOff ( ) const` [virtual, inherited]`

Turn debugging output off.

 virtual void itk::Object::DebugOn ( ) const` [virtual, inherited]`

Turn debugging output on.

 virtual void itk::LightObject::Delete ( ) ` [virtual, inherited]`

Delete an itk object. This method should always be used to delete an object when the new operator was used to create it. Using the C delete method will not work with reference counting.

 virtual bool itk::AmoebaOptimizer::GetAutomaticInitialSimplex ( ) ` [virtual]`

 virtual const ParametersType& itk::SingleValuedNonLinearVnlOptimizer::GetCachedCurrentPosition ( ) ` [virtual, inherited]`

 virtual const DerivativeType& itk::SingleValuedNonLinearVnlOptimizer::GetCachedDerivative ( ) ` [virtual, inherited]`

 virtual const MeasureType& itk::SingleValuedNonLinearVnlOptimizer::GetCachedValue ( ) ` [virtual, inherited]`

Return Cached Values. These method have the advantage of not triggering a recomputation of the metric value, but it has the disadvantage of returning a value that may not be the one corresponding to the current parameters. For GUI update purposes, this method is a good option, for mathematical validation you should rather call GetValue().

 Command* itk::Object::GetCommand ( unsigned long tag ) ` [inherited]`

Get the command associated with the given tag. NOTE: This returns a pointer to a Command, but it is safe to asign this to a Command::Pointer. Since Command inherits from LightObject, at this point in the code, only a pointer or a reference to the Command can be used.

 virtual const CostFunctionType* itk::SingleValuedNonLinearOptimizer::GetCostFunction ( ) ` [virtual, inherited]`

Get the cost function.

 CostFunctionAdaptorType* itk::SingleValuedNonLinearVnlOptimizer::GetCostFunctionAdaptor ( void ) ` [protected, inherited]`

 const CostFunctionAdaptorType* itk::SingleValuedNonLinearVnlOptimizer::GetCostFunctionAdaptor ( void ) const` [protected, inherited]`

 virtual const ParametersType& itk::Optimizer::GetCurrentPosition ( ) ` [virtual, inherited]`

Get current position of the optimization.

 bool itk::Object::GetDebug ( ) const` [inherited]`

Get the value of the debug flag.

 virtual double itk::AmoebaOptimizer::GetFunctionConvergenceTolerance ( ) ` [virtual]`

 static bool itk::Object::GetGlobalWarningDisplay ( ) ` [static, inherited]`

 virtual const ParametersType& itk::Optimizer::GetInitialPosition ( ) ` [virtual, inherited]`

Get the position to initialize the optimization.

 virtual ParametersType itk::AmoebaOptimizer::GetInitialSimplexDelta ( ) ` [virtual]`

 virtual const bool& itk::SingleValuedNonLinearVnlOptimizer::GetMaximize ( ) ` [virtual, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

 virtual unsigned int itk::AmoebaOptimizer::GetMaximumNumberOfIterations ( ) ` [virtual]`

 const MetaDataDictionary& itk::Object::GetMetaDataDictionary ( void ) const` [inherited]`

Returns:

 MetaDataDictionary& itk::Object::GetMetaDataDictionary ( void ) ` [inherited]`

Returns:
Warning:
This reference may be changed.

 bool itk::SingleValuedNonLinearVnlOptimizer::GetMinimize ( ) const` [inline, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

Definition at line 72 of file itkSingleValuedNonLinearVnlOptimizer.h.

 virtual const char* itk::AmoebaOptimizer::GetNameOfClass ( ) const` [virtual]`

Run-time type information (and related methods).

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

 CostFunctionAdaptorType* itk::SingleValuedNonLinearVnlOptimizer::GetNonConstCostFunctionAdaptor ( void ) const` [protected, inherited]`

The purpose of this method is to get around the lack of const-correctness in VNL cost-functions and optimizers

 vnl_amoeba* itk::AmoebaOptimizer::GetOptimizer ( void )

 virtual double itk::AmoebaOptimizer::GetParametersConvergenceTolerance ( ) ` [virtual]`

 virtual int itk::LightObject::GetReferenceCount ( ) const` [inline, virtual, inherited]`

Gets the reference count on this object.

Definition at line 106 of file itkLightObject.h.

 virtual const ScalesType& itk::Optimizer::GetScales ( ) ` [virtual, inherited]`

Get current parameters scaling.

 MeasureType itk::SingleValuedNonLinearOptimizer::GetValue ( const ParametersType & parameters ) const` [inherited]`

Get the cost function value at the given parameters.

Reimplemented in itk::SPSAOptimizer.

 MeasureType itk::AmoebaOptimizer::GetValue ( ) const

Return Current Value

 static void itk::Object::GlobalWarningDisplayOff ( ) ` [inline, static, inherited]`

Definition at line 100 of file itkObject.h.

References itk::Object::SetGlobalWarningDisplay().

 static void itk::Object::GlobalWarningDisplayOn ( ) ` [inline, static, inherited]`

Definition at line 98 of file itkObject.h.

References itk::Object::SetGlobalWarningDisplay().

 bool itk::Object::HasObserver ( const EventObject & event ) const` [inherited]`

Return true if an observer is registered for this event.

 void itk::Object::InvokeEvent ( const EventObject & ) const` [inherited]`

Call Execute on all the Commands observing this event id. The actions triggered by this call doesn't modify this object.

 void itk::Object::InvokeEvent ( const EventObject & ) ` [inherited]`

Call Execute on all the Commands observing this event id.

 virtual void itk::SingleValuedNonLinearVnlOptimizer::MaximizeOff ( ) ` [virtual, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

 virtual void itk::SingleValuedNonLinearVnlOptimizer::MaximizeOn ( ) ` [virtual, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

 void itk::SingleValuedNonLinearVnlOptimizer::MinimizeOff ( void ) ` [inline, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

Definition at line 78 of file itkSingleValuedNonLinearVnlOptimizer.h.

 void itk::SingleValuedNonLinearVnlOptimizer::MinimizeOn ( void ) ` [inline, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

Definition at line 76 of file itkSingleValuedNonLinearVnlOptimizer.h.

 static Pointer itk::AmoebaOptimizer::New ( ) ` [static]`

Method for creation through the object factory.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

 void itk::LightObject::Print ( std::ostream & os, Indent indent = `0` ) const` [inherited]`

Cause the object to print itself out.

Referenced by itk::WeakPointer< itk::ProcessObject >::Print().

 virtual void itk::LightObject::PrintHeader ( std::ostream & os, Indent indent ) const` [protected, virtual, inherited]`

 bool itk::Object::PrintObservers ( std::ostream & os, Indent indent ) const` [protected, inherited]`

 void itk::AmoebaOptimizer::PrintSelf ( std::ostream & os, Indent indent ) const` [protected, virtual]`

Print out internal state

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

 virtual void itk::LightObject::PrintTrailer ( std::ostream & os, Indent indent ) const` [protected, virtual, inherited]`

 virtual void itk::Object::Register ( ) const` [virtual, inherited]`

Increase the reference count (mark as used by another object).

Reimplemented from itk::LightObject.

 void itk::Object::RemoveAllObservers ( ) ` [inherited]`

Remove all observers .

 void itk::Object::RemoveObserver ( unsigned long tag ) ` [inherited]`

Remove the observer with this tag value.

 virtual void itk::AmoebaOptimizer::SetAutomaticInitialSimplex ( bool _arg ) ` [virtual]`

Set/Get the mode which determines how the amoeba algorithm defines the initial simplex. Default is AutomaticInitialSimplexOn. If AutomaticInitialSimplex is on, the initial simplex is created with a default size. If AutomaticInitialSimplex is off, then InitialSimplexDelta will be used to define the initial simplex, setting the ith corner of the simplex as [x0[0], x0[1], ..., x0[i]+InitialSimplexDelta[i], ..., x0[d-1]].

 virtual void itk::SingleValuedNonLinearOptimizer::SetCostFunction ( CostFunctionType * costFunction ) ` [virtual, inherited]`

Set the cost function.

 virtual void itk::AmoebaOptimizer::SetCostFunction ( SingleValuedCostFunction * costFunction ) ` [virtual]`

Plug in a Cost Function into the optimizer

Implements itk::SingleValuedNonLinearVnlOptimizer.

 void itk::SingleValuedNonLinearVnlOptimizer::SetCostFunctionAdaptor ( CostFunctionAdaptorType * adaptor ) ` [protected, inherited]`

 virtual void itk::Optimizer::SetCurrentPosition ( const ParametersType & param ) ` [protected, virtual, inherited]`

Set the current position.

 void itk::Object::SetDebug ( bool debugFlag ) const` [inherited]`

Set the value of the debug flag. A non-zero value turns debugging on.

 virtual void itk::AmoebaOptimizer::SetFunctionConvergenceTolerance ( double tol ) ` [virtual]`

 static void itk::Object::SetGlobalWarningDisplay ( bool flag ) ` [static, inherited]`

This is a global flag that controls whether any debug, warning or error messages are displayed.

Referenced by itk::Object::GlobalWarningDisplayOff(), and itk::Object::GlobalWarningDisplayOn().

 virtual void itk::Optimizer::SetInitialPosition ( const ParametersType & param ) ` [virtual, inherited]`

Set the position to initialize the optimization.

 virtual void itk::AmoebaOptimizer::SetInitialSimplexDelta ( ParametersType _arg ) ` [virtual]`

Set/Get the deltas that are used to define the initial simplex when AutomaticInitialSimplex is off.

 virtual void itk::SingleValuedNonLinearVnlOptimizer::SetMaximize ( bool _arg ) ` [virtual, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

 virtual void itk::AmoebaOptimizer::SetMaximumNumberOfIterations ( unsigned int n ) ` [virtual]`

Set/Get the maximum number of iterations. The optimization algorithm will terminate after the maximum number of iterations has been reached. The default value is 500.

 void itk::Object::SetMetaDataDictionary ( const MetaDataDictionary & rhs ) ` [inherited]`

Returns:

 void itk::SingleValuedNonLinearVnlOptimizer::SetMinimize ( bool v ) ` [inline, inherited]`

Methods to define whether the cost function will be maximized or minimized. By default the VNL amoeba optimizer is only a minimizer. Maximization is implemented here by notifying the CostFunctionAdaptor which in its turn will multiply the function values and its derivative by -1.0.

Definition at line 74 of file itkSingleValuedNonLinearVnlOptimizer.h.

 virtual void itk::AmoebaOptimizer::SetParametersConvergenceTolerance ( double tol ) ` [virtual]`

The optimization algorithm will terminate when the simplex diameter and the difference in cost function at the corners of the simplex falls below user specified thresholds. The simplex diameter threshold is set via method SetParametersConvergenceTolerance() with the default value being 1e-8. The cost function convergence threshold is set via method SetFunctionConvergenceTolerance() with the default value being 1e-4.

 virtual void itk::Object::SetReferenceCount ( int ) ` [virtual, inherited]`

Sets the reference count (use with care)

Reimplemented from itk::LightObject.

 void itk::Optimizer::SetScales ( const ScalesType & scales ) ` [inherited]`

Set current parameters scaling.

 void itk::AmoebaOptimizer::StartOptimization ( void ) ` [virtual]`

Start optimization with an initial value.

Reimplemented from itk::Optimizer.

 virtual void itk::Object::UnRegister ( ) const` [virtual, inherited]`

Decrease the reference count (release by another object).

Reimplemented from itk::LightObject.

## Member Data Documentation

 CostFunctionPointer itk::SingleValuedNonLinearOptimizer::m_CostFunction` [protected, inherited]`

Definition at line 80 of file itkSingleValuedNonLinearOptimizer.h.

 ParametersType itk::Optimizer::m_CurrentPosition` [protected, inherited]`

Definition at line 95 of file itkOptimizer.h.

 InternalReferenceCountType itk::LightObject::m_ReferenceCount` [mutable, protected, inherited]`

Number of uses of this object by other objects.

Definition at line 144 of file itkLightObject.h.

 SimpleFastMutexLock itk::LightObject::m_ReferenceCountLock` [mutable, protected, inherited]`

Mutex lock to protect modification to the reference count

Definition at line 147 of file itkLightObject.h.

 bool itk::Optimizer::m_ScalesInitialized` [protected, inherited]`

Definition at line 90 of file itkOptimizer.h.

The documentation for this class was generated from the following file:
Generated at Thu Nov 6 01:22:46 2008 for ITK by 1.5.1 written by Dimitri van Heesch, © 1997-2000