PLearn::PCA Class Reference

#include <PCA.h>

Inheritance diagram for PLearn::PCA:

[legend]Collaboration diagram for PLearn::PCA:

[legend]List of all members.


Public Member Functions
	PCA ()
	Default constructor.
virtual void	build ()
	Simply calls inherited::build() then build_().
virtual void	makeDeepCopyFromShallowCopy (map< const void , void > &copies)
	Transforms a shallow copy into a deep copy.
	PLEARN_DECLARE_OBJECT (PCA)
virtual int	outputsize () const
	returns the size of this learner's output, (which typically may depend on its inputsize(), targetsize() and set options)
virtual void	forget ()
	(Re-)initializes the PLearner in its fresh state (that state may depend on the 'seed' option) And sets 'stage' back to 0 (this is the stage of a fresh learner!)
virtual void	train ()
	The role of the train method is to bring the learner up to stage==nstages, updating the train_stats collector with training costs measured on-line in the process.
virtual void	computeOutput (const Vec &input, Vec &output) const
	Computes the output from the input.
void	reconstruct (const Vec &output, Vec &input) const
	Reconstructs an input from a (possibly partial) output (i.e. the first few princial components kept).
virtual void	computeCostsFromOutputs (const Vec &input, const Vec &output, const Vec &target, Vec &costs) const
	Computes the costs from already computed output.
virtual TVec< string >	getTestCostNames () const
	Returns [ "squared_reconstruction_error" ].
virtual TVec< string >	getTrainCostNames () const
	No trian costs are computed for this learner.
Public Attributes
string	algo
int	ncomponents
real	sigmasq
	The number of principal components to keep (that's also the outputsize).
bool	normalize
	This gets added to the diagonal of the covariance matrix prior to eigen-decomposition.
Vec	mu
	If true, we divide by sqrt(eigenval) after projecting on the eigenvec.
Vec	eigenvals
	The (weighted) mean of the samples.
Mat	eigenvecs
	The ncomponents eigenvalues corresponding to the principal directions kept.
Static Protected Member Functions
void	declareOptions (OptionList &ol)
	Declares this class' options.
Private Types
typedef PLearner	inherited
Private Member Functions
void	build_ ()
	This does the actual building.

Member Typedef Documentation

typedef PLearner PLearn::PCA::inherited [private]

Reimplemented from PLearn::PLearner.
Definition at line 53 of file PCA.h.

Constructor & Destructor Documentation

PLearn::PCA::PCA ( )

Default constructor.

Definition at line 50 of file PCA.cc.
References PLearn::normalize().

Member Function Documentation

void PLearn::PCA::build ( ) [virtual]

Simply calls inherited::build() then build_().

Reimplemented from PLearn::PLearner.
Definition at line 102 of file PCA.cc.
References build_().

void PLearn::PCA::build_ ( ) [private]

This does the actual building.

Reimplemented from PLearn::PLearner.
Definition at line 111 of file PCA.cc.
Referenced by build().

void PLearn::PCA::computeCostsFromOutputs ( const Vec & input,

const Vec & output,

const Vec & target,

Vec & costs

) const [virtual]

Computes the costs from already computed output.
The only computed cost is the squared_reconstruction_error
Implements PLearn::PLearner.
Definition at line 118 of file PCA.cc.
References PLearn::powdistance(), reconstruct(), PLearn::TVec< T >::resize(), and PLearn::Vec.

void PLearn::PCA::computeOutput ( const Vec & input,

Vec & output

) const [virtual]

Computes the output from the input.

Implements PLearn::PLearner.
Definition at line 130 of file PCA.cc.
References PLearn::dot(), eigenvals, eigenvecs, PLearn::TVec< T >::length(), mu, ncomponents, normalize, PLearn::TVec< T >::resize(), PLearn::sqrt(), and x.

void PLearn::PCA::declareOptions ( OptionList & ol ) [static, protected]

Declares this class' options.

Reimplemented from PLearn::PLearner.
Definition at line 69 of file PCA.cc.
References PLearn::declareOption(), and PLearn::OptionList.

void PLearn::PCA::forget ( ) [virtual]

(Re-)initializes the PLearner in its fresh state (that state may depend on the 'seed' option) And sets 'stage' back to 0 (this is the stage of a fresh learner!)

Implements PLearn::PLearner.
Definition at line 153 of file PCA.cc.

TVec< string > PLearn::PCA::getTestCostNames ( ) const [virtual]

Returns [ "squared_reconstruction_error" ].

Implements PLearn::PLearner.
Definition at line 161 of file PCA.cc.

TVec< string > PLearn::PCA::getTrainCostNames ( ) const [virtual]

No trian costs are computed for this learner.

Implements PLearn::PLearner.
Definition at line 169 of file PCA.cc.

void PLearn::PCA::makeDeepCopyFromShallowCopy ( map< const void *, void * > & copies ) [virtual]

Transforms a shallow copy into a deep copy.

Definition at line 177 of file PCA.cc.
References PLearn::deepCopyField(), eigenvals, eigenvecs, and mu.

int PLearn::PCA::outputsize ( ) const [virtual]

returns the size of this learner's output, (which typically may depend on its inputsize(), targetsize() and set options)

Implements PLearn::PLearner.
Definition at line 189 of file PCA.cc.
References ncomponents.

PLearn::PCA::PLEARN_DECLARE_OBJECT ( PCA )

void PLearn::PCA::reconstruct ( const Vec & output,

Vec & input

) const

Reconstructs an input from a (possibly partial) output (i.e. the first few princial components kept).

Definition at line 368 of file PCA.cc.
References eigenvals, eigenvecs, PLearn::TVec< T >::length(), mu, PLearn::multiplyAcc(), normalize, PLearn::TVec< T >::resize(), and PLearn::sqrt().
Referenced by computeCostsFromOutputs().

void PLearn::PCA::train ( ) [virtual]

The role of the train method is to bring the learner up to stage==nstages, updating the train_stats collector with training costs measured on-line in the process.

Implements PLearn::PLearner.
Definition at line 197 of file PCA.cc.
References PLearn::abs(), algo, PLearn::computeInputMeanAndCovar(), PLearn::computeMeanAndVariance(), PLearn::dot(), eigenvals, PLearn::eigenVecOfSymmMat(), eigenvecs, PLearn::fill_random_normal(), PLearn::GramSchmidtOrthogonalization(), k, PLearn::TVec< T >::length(), PLearn::VMat::length(), PLearn::matInvert(), mu, ncomponents, PLearn::negateElements(), PLearn::normalize(), normalize, PLERROR, PLWARNING, PLearn::product(), PLearn::productAcc(), PLearn::productTranspose(), PLearn::TMat< T >::resize(), PLearn::TVec< T >::resize(), PLearn::PLearner::setTrainingSet(), PLearn::TMat< T >::subMatColumns(), PLearn::TMat< T >::subMatRows(), PLearn::VMat::toMat(), PLearn::transposeProduct(), and PLearn::ProgressBar::update().

Member Data Documentation

string PLearn::PCA::algo

Definition at line 61 of file PCA.h.
Referenced by train().

Vec PLearn::PCA::eigenvals

The (weighted) mean of the samples.

Definition at line 68 of file PCA.h.
Referenced by computeOutput(), makeDeepCopyFromShallowCopy(), reconstruct(), and train().

Mat PLearn::PCA::eigenvecs

The ncomponents eigenvalues corresponding to the principal directions kept.

Definition at line 69 of file PCA.h.
Referenced by computeOutput(), makeDeepCopyFromShallowCopy(), reconstruct(), and train().

Vec PLearn::PCA::mu

If true, we divide by sqrt(eigenval) after projecting on the eigenvec.

Definition at line 67 of file PCA.h.
Referenced by computeOutput(), makeDeepCopyFromShallowCopy(), reconstruct(), and train().

int PLearn::PCA::ncomponents

Definition at line 62 of file PCA.h.
Referenced by computeOutput(), outputsize(), and train().

bool PLearn::PCA::normalize

This gets added to the diagonal of the covariance matrix prior to eigen-decomposition.

Definition at line 64 of file PCA.h.
Referenced by computeOutput(), reconstruct(), and train().

real PLearn::PCA::sigmasq

The number of principal components to keep (that's also the outputsize).

Definition at line 63 of file PCA.h.

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

Generated on Tue Aug 17 16:28:00 2004 for PLearn by

1.3.7

PLearn::PCA Class Reference

Public Member Functions

Public Attributes

Static Protected Member Functions

Private Types

Private Member Functions

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation