GClasses::GParticleSwarm Class Reference

Detailed Description

An optimization algorithm inspired by flocking birds.

#include <GParticleSwarm.h>

Inheritance diagram for GClasses::GParticleSwarm:

Public Member Functions
	GParticleSwarm (GTargetFunction *pCritic, size_t nPopulation, double dMin, double dRange, GRand *pRand)
virtual	~GParticleSwarm ()
virtual double	iterate ()
	Perform a little more optimization. More...
void	setLearningRate (double d)
	Specify the learning rate. More...
Public Member Functions inherited from GClasses::GOptimizer
	GOptimizer (GTargetFunction *pCritic)
virtual	~GOptimizer ()
void	basicTest (double minAccuracy, double warnRange=0.001)
	This is a helper method used by the unit tests of several model learners. More...
virtual const GVec &	currentVector ()=0
	Returns the current vector of the optimizer. For greedy search methods, this will be the best vector yet found. More...
double	searchUntil (size_t nBurnInIterations, size_t nIterations, double dImprovement)
	This will first call iterate() nBurnInIterations times, then it will repeatedly call iterate() in blocks of nIterations times. If the error heuristic has not improved by the specified ratio after a block of iterations, it will stop. (For example, if the error before the block of iterations was 50, and the error after is 49, then training will stop if dImprovement is > 0.02.) If the error heuristic is not stable, then the value of nIterations should be large. More...

Protected Member Functions
void	reset ()

Protected Attributes
double	m_dLearningRate
double	m_dMin
double	m_dRange
size_t	m_nDimensions
size_t	m_nGlobalBest
size_t	m_nPopulation
GMatrix	m_pBests
GVec	m_pErrors
GMatrix	m_pPositions
GRand *	m_pRand
GMatrix	m_pVelocities
Protected Attributes inherited from GClasses::GOptimizer
GTargetFunction *	m_pCritic

Constructor & Destructor Documentation

GClasses::GParticleSwarm::GParticleSwarm	(	GTargetFunction *	pCritic,
		size_t	nPopulation,
		double	dMin,
		double	dRange,
		GRand *	pRand
	)

virtual GClasses::GParticleSwarm::~GParticleSwarm ( )

virtual

Member Function Documentation

virtual double GClasses::GParticleSwarm::iterate ( )

virtual

Perform a little more optimization.

Implements GClasses::GOptimizer.

void GClasses::GParticleSwarm::reset ( )

protected

void GClasses::GParticleSwarm::setLearningRate ( double  d )

inline

Specify the learning rate.

Member Data Documentation

double GClasses::GParticleSwarm::m_dLearningRate

protected

double GClasses::GParticleSwarm::m_dMin

protected

double GClasses::GParticleSwarm::m_dRange

protected

size_t GClasses::GParticleSwarm::m_nDimensions

protected

size_t GClasses::GParticleSwarm::m_nGlobalBest

protected

size_t GClasses::GParticleSwarm::m_nPopulation

protected

GMatrix GClasses::GParticleSwarm::m_pBests

protected

GVec GClasses::GParticleSwarm::m_pErrors

protected

GMatrix GClasses::GParticleSwarm::m_pPositions

protected

GRand* GClasses::GParticleSwarm::m_pRand

protected

GMatrix GClasses::GParticleSwarm::m_pVelocities

protected