Implements the well-known indicator-based selection strategy. More...

#include <shark/Algorithms/DirectSearch/Operators/Selection/IndicatorBasedSelection.h>

Public Member Functions
template<typename PopulationType >
void	operator() (PopulationType &population, std::size_t mu)
	Executes the algorithm and assigns each member of the population its level non-dominance (rank) and its individual contribution to the front it belongs to (share).

template<typename Archive >
void	serialize (Archive &archive, const unsigned int version)
	Stores/restores the serializer's state.

Indicator &	indicator ()

Indicator const &	indicator () const

Detailed Description

template<typename Indicator>
struct shark::IndicatorBasedSelection< Indicator >

Implements the well-known indicator-based selection strategy.

See Kalyanmoy Deb and Amrit Pratap and Sameer Agarwal and T. Meyarivan, A Fast Elitist Multi-Objective Genetic Algorithm: NSGA-II, IEEE Transactions on Evolutionary Computation Year 2000, Volume 6, p. 182-197

Template Parameters

Indicator The second-level sorting criterion.

Definition at line 54 of file IndicatorBasedSelection.h.

Member Function Documentation

◆ indicator() [1/2]

template<typename Indicator >

Indicator & shark::IndicatorBasedSelection< Indicator >::indicator ( )

inline

Definition at line 121 of file IndicatorBasedSelection.h.

Referenced by shark::SMSEMOA::indicator(), and shark::SMSEMOA::indicator().

◆ indicator() [2/2]

template<typename Indicator >

Indicator const & shark::IndicatorBasedSelection< Indicator >::indicator ( ) const

inline

Definition at line 124 of file IndicatorBasedSelection.h.

◆ operator()()

template<typename Indicator >

template<typename PopulationType >

void shark::IndicatorBasedSelection< Indicator >::operator()	(	PopulationType &	population,
		std::size_t	mu
	)

inline

Executes the algorithm and assigns each member of the population its level non-dominance (rank) and its individual contribution to the front it belongs to (share).

Parameters

[in,out]	population	The population to be ranked.
[in,out]	mu	the number of individuals to select

Definition at line 64 of file IndicatorBasedSelection.h.

References shark::nonDominatedSort(), shark::penalizedFitness(), and shark::ranks().

◆ serialize()

template<typename Indicator >

template<typename Archive >

void shark::IndicatorBasedSelection< Indicator >::serialize	(	Archive &	archive,
		const unsigned int	version
	)

inline

Stores/restores the serializer's state.

Template Parameters

Archive Type of the archive.

Parameters

[in,out]	archive	The archive to serialize to.
[in]	version	number, currently unused.

Definition at line 117 of file IndicatorBasedSelection.h.

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

include/shark/Algorithms/DirectSearch/Operators/Selection/IndicatorBasedSelection.h

Public Member Functions

Detailed Description

Member Function Documentation

◆ indicator() [1/2]

◆ indicator() [2/2]

◆ operator()()

◆ serialize()