lti::SOFM2D Class Reference

This is a Self-Organizing Feature Map with a 2-D grid of neurons. More...

#include <ltiSOFM2D.h>

Inheritance diagram for lti::SOFM2D:

[legend]

Collaboration diagram for lti::SOFM2D:

[legend]

List of all members.

Classes
class	parameters
	the parameters for the class SOFM2D More...
Public Member Functions
	SOFM2D ()
	SOFM2D (const SOFM2D &other)
virtual	~SOFM2D ()
virtual const char *	getTypeName () const
SOFM2D &	copy (const SOFM2D &other)
SOFM2D &	operator= (const SOFM2D &other)
virtual classifier *	clone () const
const parameters &	getParameters () const
virtual bool	train (const dmatrix &input, ivector &ids)
virtual bool	train (const dmatrix &input)
virtual bool	classify (const dvector &feature, outputVector &result) const
point	size () const
int	xSize () const
int	ySize () const
virtual bool	write (ioHandler &handler, const bool complete=true) const
virtual bool	read (ioHandler &handler, const bool complete=true)
Protected Member Functions
bool	calcSize (const dmatrix &data)
bool	initGrid (const dmatrix &data)
void	getNeighborhoodKernel (const int &maxN, kernel2D< double > &facN)
bool	trainDist (const dmatrix &data)
bool	trainDot (const dmatrix &data)
Protected Attributes
int	sizeX
int	sizeY
double	eva1
double	eva2
dvector	eve1
dvector	eve2

Detailed Description

This is a Self-Organizing Feature Map with a 2-D grid of neurons.

Constructor & Destructor Documentation

lti::SOFM2D::SOFM2D ( )

default constructor

lti::SOFM2D::SOFM2D ( const SOFM2D & other )

copy constructor

Parameters:

other

the object to be copied

virtual lti::SOFM2D::~SOFM2D ( ) [virtual]

destructor

Member Function Documentation

bool lti::SOFM2D::calcSize ( const dmatrix & data ) [protected]

calculate sizeX and sizeY in case of param.calulateSize is true

virtual bool lti::SOFM2D::classify	(	const dvector &	feature,
		outputVector &	result
	)			const `[virtual]`

Classification.

Classifies the feature and returns the outputVector with the classification result.

Parameters:

	feature	the vector to be classified
	result	the result of the classification

Returns:: false if an error occurred during classification else true

Implements lti::SOFM.

Referenced by lti::SOFM2DVisualizer::drawClasses(), and lti::SOFM2DVisualizer::drawHits().

virtual classifier* lti::SOFM2D::clone ( ) const [virtual]

returns a pointer to a clone of this classifier.

Implements lti::SOFM.

SOFM2D& lti::SOFM2D::copy ( const SOFM2D & other )

copy data of "other" classifier.

Parameters:

other

the classifier to be copied

Returns:: a reference to this classifier object

Reimplemented from lti::SOFM.

void lti::SOFM2D::getNeighborhoodKernel	(	const int &	maxN,
		kernel2D< double > &	facN
	)			`[protected]`

calculate the neigborhood kernel

const parameters& lti::SOFM2D::getParameters ( ) const

returns used parameters

Reimplemented from lti::SOFM.

virtual const char* lti::SOFM2D::getTypeName ( ) const [virtual]

returns the name of this type ("SOFM2D")

Reimplemented from lti::SOFM.

bool lti::SOFM2D::initGrid ( const dmatrix & data ) [protected]

initializes the grid according to parameters.initType

SOFM2D& lti::SOFM2D::operator= ( const SOFM2D & other )

alias for copy member

Parameters:

other

the classifier to be copied

Returns:: a reference to this classifier object

Reimplemented from lti::SOFM.

virtual bool lti::SOFM2D::read	(	ioHandler &	handler,
		const bool	complete = `true`
	)			`[virtual]`

read the SOFM2D from the given ioHandler

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.

Returns:: true if write was successful

Reimplemented from lti::SOFM.

point lti::SOFM2D::size ( ) const [inline]

returns the size (x,y) of the feature map.

References sizeX, and sizeY.

virtual bool lti::SOFM2D::train ( const dmatrix & input ) [virtual]

Unsupervised training.

The row vectors in the input matrix are used for training of the classifier.

Parameters:

input

the matrix with the input vectors (each row is a training vector)

Returns:: true if successful, false otherwise. (if false you can check the error message with getStatusString())

Implements lti::SOFM.

virtual bool lti::SOFM2D::train	(	const dmatrix &	input,
		ivector &	ids
	)			`[virtual]`

Unsupervised training.

The vectors in the input matrix will be put into groups according to the training algorithm. Additionally, an integer indicating the class each point belongs to is returned.

By default this method uses the other train method train(const dmatrix&) and then calls classify(const dvector&) to get the ids for each trainvector. These ids are then returned.

Parameters:

	input	the matrix with the input vectors (each row is a training vector)
	ids	vector of class ids for each input point

Returns:: true if successful, false otherwise. (if false you can check the error message with getStatusString())

Reimplemented from lti::SOFM.

bool lti::SOFM2D::trainDist ( const dmatrix & data ) [protected]

train the SOFM using L1- or L2-Norm

bool lti::SOFM2D::trainDot ( const dmatrix & data ) [protected]

train the SOFM using dot product

virtual bool lti::SOFM2D::write	(	ioHandler &	handler,
		const bool	complete = `true`
	)			const `[virtual]`

write the SOFM2D in the given ioHandler

Parameters:

	handler	the ioHandler to be used
	complete	if true (the default) the enclosing begin/end will be also written, otherwise only the data block will be written.