lti::lvq::parameters Class Reference

the parameters for the class classifier More...

#include <ltiLvq.h>

Inheritance diagram for lti::lvq::parameters:

[legend]

Collaboration diagram for lti::lvq::parameters:

[legend]

List of all members.

Public Types
enum	eLvqInit { LvqRand, LvqMaxDist }
Public Member Functions
	parameters ()
	parameters (const parameters &other)
virtual	~parameters ()
const char *	getTypeName () const
parameters &	copy (const parameters &other)
parameters &	operator= (const parameters &other)
virtual classifier::parameters *	clone () const
Public Attributes
double	learnRate1
double	learnRate2
double	learnRateFactor
double	windowSize
int	nbNeuronsPerClass
int	nbPresentations1
int	nbPresentations2
eNormType	norm
eLvqInit	initType
bool	flagOlvq1
bool	flagOlvq3
double	sigmaFactor
bool	doStatistics
std::string	statisticsFilename
std::string	netFilename
bool	doTrain2
bool	saveBest
bool	correctVs3Best

---

Detailed Description

the parameters for the class classifier

---

Member Enumeration Documentation

enum lti::lvq::parameters::eLvqInit

enumeration to specify the network initialization types.

Enumerator:

LvqRand	random initialization of the vector code
LvqMaxDist	initialization with the maximum distance

---

Constructor & Destructor Documentation

lti::lvq::parameters::parameters

(

)

default constructor

Reimplemented from lti::classifier::parameters.

lti::lvq::parameters::parameters

(

const parameters &

other

)

copy constructor

Parameters:

other

the parameters object to be copied

virtual lti::lvq::parameters::~parameters

(

)

[virtual]

destructor

Reimplemented from lti::classifier::parameters.

---

Member Function Documentation

virtual classifier::parameters* lti::lvq::parameters::clone

(

)

const [virtual]

returns a pointer to a clone of the parameters

Reimplemented from lti::classifier::parameters.

parameters& lti::lvq::parameters::copy

(

const parameters &

other

)

copy the contents of a parameters object

Parameters:

other

the parameters object to be copied

Returns:

a reference to this parameters object

Referenced by operator=().

const char* lti::lvq::parameters::getTypeName

(

)

const [virtual]

returns name of this type

Reimplemented from lti::classifier::parameters.

parameters& lti::lvq::parameters::operator=

(

const parameters &

other

)

[inline]

Alias for copy.

Parameters:

other

the parameters object to be copied

Returns:

a reference to this parameters object

References copy().

---

Member Data Documentation

bool lti::lvq::parameters::correctVs3Best

if saveBest is true, and correctVs3Best is also true, the best net with the correct result will be saved.

If correctVs3Best is false, the best "three-best" network will be saved. If saveBest is false, this parameter will be ignored.

bool lti::lvq::parameters::doStatistics

generate training statistics

bool lti::lvq::parameters::doTrain2

has something to do with the statistics.

.. (ask P. Doerfler)

bool lti::lvq::parameters::flagOlvq1

if true, the OLVQ1 algorithm will be used for the first presentation set.

Otherwise the LVQ1 will be used.

bool lti::lvq::parameters::flagOlvq3

if true, the OLVQ3 algorithm will be used for the second presentation set.

Otherwise the LVQ3 will be used.

eLvqInit lti::lvq::parameters::initType

specify the way the codebook vectors should be initialized

double lti::lvq::parameters::learnRate1

learn rate for LVQ1 or OLVQ1

double lti::lvq::parameters::learnRate2

learn rate for LVQ3 or OLVQ3

double lti::lvq::parameters::learnRateFactor

learn rate factor used in LVQ3 and OLVQ3 to change the learn rate

int lti::lvq::parameters::nbNeuronsPerClass

number of neurons per class

Referenced by lti::lvq::getDimOutputLayer().

int lti::lvq::parameters::nbPresentations1

number of presentations for LVQ1 or OLVQ1

int lti::lvq::parameters::nbPresentations2

number of presentations for LVQ3 or OLVQ3

std::string lti::lvq::parameters::netFilename

file name for the network

eNormType lti::lvq::parameters::norm

the norm type (L1-, L2-norm)

bool lti::lvq::parameters::saveBest

if true, the "best" network will be saved (see also correctVs3Best)

double lti::lvq::parameters::sigmaFactor

sigma factor

std::string lti::lvq::parameters::statisticsFilename

name of the file where the statistics will be saved

double lti::lvq::parameters::windowSize

window size

---

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

• ltiLvq.h