PLearn::TangentLearner Class Reference

#include <TangentLearner.h>

Inheritance diagram for PLearn::TangentLearner:

[legend]Collaboration diagram for PLearn::TangentLearner:

[legend]List of all members.


Public Member Functions
	TangentLearner ()
	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 (TangentLearner)
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	initializeParams ()
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.
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 the names of the costs computed by computeCostsFromOutpus (and thus the test method).
virtual TVec< string >	getTrainCostNames () const
	Returns the names of the objective costs that the train method computes and for which it updates the VecStatsCollector train_stats.
Public Attributes
string	training_targets
bool	use_subspace_distance
bool	normalize_by_neighbor_distance
bool	ordered_vectors
real	smart_initialization
real	initialization_regularization
int	n_neighbors
int	n_dim
PP< Optimizer >	optimizer
Var	embedding
Func	output_f
Func	tangent_predictor
Func	projection_error_f
string	architecture_type
string	output_type
int	n_hidden_units
int	batch_size
real	norm_penalization
real	svd_threshold
real	projection_error_regularization
Static Protected Member Functions
void	declareOptions (OptionList &ol)
	Declares this class' options.
Protected Attributes
Func	cost_of_one_example
Var	b
Var	W
Var	c
Var	V
Var	tangent_targets
VarArray	parameters
Private Types
typedef PLearner	inherited
Private Member Functions
void	build_ ()
	This does the actual building.

Member Typedef Documentation

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

Reimplemented from PLearn::PLearner.
Definition at line 59 of file TangentLearner.h.

Constructor & Destructor Documentation

PLearn::TangentLearner::TangentLearner ( )

Default constructor.

Definition at line 96 of file TangentLearner.cc.

Member Function Documentation

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

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

Reimplemented from PLearn::PLearner.
Definition at line 347 of file TangentLearner.cc.
References build_().

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

This does the actual building.

Reimplemented from PLearn::PLearner.
Definition at line 252 of file TangentLearner.cc.
References architecture_type, cost_of_one_example, PLearn::diagonalized_factors_product(), embedding, n_dim, n_hidden_units, n_neighbors, PLearn::VarArray::nelems(), norm_penalization, normalize_by_neighbor_distance, ordered_vectors, output_f, output_type, parameters, PLERROR, PLearn::product(), PLearn::projection_error(), projection_error_f, projection_error_regularization, PLearn::TVec< Var >::resize(), PLearn::TVec< Var >::size(), svd_threshold, tangent_predictor, tangent_targets, PLearn::tanh(), training_targets, use_subspace_distance, V, W, and x.
Referenced by build().

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

const Vec & output,

const Vec & target,

Vec & costs

) const [virtual]

Computes the costs from already computed output.

Implements PLearn::PLearner.
Definition at line 506 of file TangentLearner.cc.
References PLERROR.

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

Vec & output

) const [virtual]

Computes the output from the input.

Implements PLearn::PLearner.
Definition at line 499 of file TangentLearner.cc.
References output_f, outputsize(), PLearn::TVec< T >::resize(), and PLearn::Vec.

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

Declares this class' options.

Reimplemented from PLearn::PLearner.
Definition at line 153 of file TangentLearner.cc.
References PLearn::declareOption(), and PLearn::OptionList.

void PLearn::TangentLearner::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 375 of file TangentLearner.cc.
References initializeParams().

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

Returns the names of the costs computed by computeCostsFromOutpus (and thus the test method).

Implements PLearn::PLearner.
Definition at line 512 of file TangentLearner.cc.
References getTrainCostNames().

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

Returns the names of the objective costs that the train method computes and for which it updates the VecStatsCollector train_stats.

Implements PLearn::PLearner.
Definition at line 517 of file TangentLearner.cc.
Referenced by getTestCostNames().

void PLearn::TangentLearner::initializeParams ( ) [virtual]

Definition at line 444 of file TangentLearner.cc.
References architecture_type, PLearn::fill_random_uniform(), initialization_regularization, PLearn::PLearner::inputsize(), PLearn::manual_seed(), n_hidden_units, optimizer, PLERROR, PLearn::seed(), smart_initialization, PLearn::smartInitialization(), PLearn::sqrt(), V, and W.
Referenced by forget().

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

Transforms a shallow copy into a deep copy.

Definition at line 355 of file TangentLearner.cc.
References cost_of_one_example, PLearn::deepCopyField(), optimizer, parameters, tangent_predictor, tangent_targets, V, PLearn::varDeepCopyField(), and W.

int PLearn::TangentLearner::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 370 of file TangentLearner.cc.
References output_f.
Referenced by computeOutput().

PLearn::TangentLearner::PLEARN_DECLARE_OBJECT ( TangentLearner )

void PLearn::TangentLearner::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 381 of file TangentLearner.cc.
References batch_size, cost_of_one_example, PLearn::endl(), PLearn::hconcat(), PLearn::PLearner::inputsize(), PLearn::VMat::length(), PLearn::local_neighbors_differences(), PLearn::meanOf(), n_neighbors, optimizer, parameters, PLERROR, PLearn::tostring(), training_targets, and PLearn::ProgressBar::update().

Member Data Documentation

string PLearn::TangentLearner::architecture_type

Definition at line 99 of file TangentLearner.h.
Referenced by build_(), and initializeParams().

Var PLearn::TangentLearner::b [protected]

Definition at line 65 of file TangentLearner.h.

int PLearn::TangentLearner::batch_size

Definition at line 103 of file TangentLearner.h.
Referenced by train().

Var PLearn::TangentLearner::c [protected]

Definition at line 65 of file TangentLearner.h.

Func PLearn::TangentLearner::cost_of_one_example [protected]

Definition at line 64 of file TangentLearner.h.
Referenced by build_(), makeDeepCopyFromShallowCopy(), and train().

Var PLearn::TangentLearner::embedding

Definition at line 93 of file TangentLearner.h.
Referenced by build_().

real PLearn::TangentLearner::initialization_regularization

Definition at line 88 of file TangentLearner.h.
Referenced by initializeParams().

int PLearn::TangentLearner::n_dim

Definition at line 90 of file TangentLearner.h.
Referenced by build_().

int PLearn::TangentLearner::n_hidden_units

Definition at line 101 of file TangentLearner.h.
Referenced by build_(), and initializeParams().

int PLearn::TangentLearner::n_neighbors

Definition at line 89 of file TangentLearner.h.
Referenced by build_(), and train().

real PLearn::TangentLearner::norm_penalization

Definition at line 105 of file TangentLearner.h.
Referenced by build_().

bool PLearn::TangentLearner::normalize_by_neighbor_distance

Definition at line 85 of file TangentLearner.h.
Referenced by build_().

PP<Optimizer> PLearn::TangentLearner::optimizer

Definition at line 92 of file TangentLearner.h.
Referenced by initializeParams(), makeDeepCopyFromShallowCopy(), and train().

bool PLearn::TangentLearner::ordered_vectors

Definition at line 86 of file TangentLearner.h.
Referenced by build_().

Func PLearn::TangentLearner::output_f

Definition at line 94 of file TangentLearner.h.
Referenced by build_(), computeOutput(), and outputsize().

string PLearn::TangentLearner::output_type

Definition at line 100 of file TangentLearner.h.
Referenced by build_().

VarArray PLearn::TangentLearner::parameters [protected]

Definition at line 73 of file TangentLearner.h.
Referenced by build_(), makeDeepCopyFromShallowCopy(), and train().

Func PLearn::TangentLearner::projection_error_f

Definition at line 96 of file TangentLearner.h.
Referenced by build_().

real PLearn::TangentLearner::projection_error_regularization

Definition at line 107 of file TangentLearner.h.
Referenced by build_().

real PLearn::TangentLearner::smart_initialization

Definition at line 87 of file TangentLearner.h.
Referenced by initializeParams().

real PLearn::TangentLearner::svd_threshold

Definition at line 106 of file TangentLearner.h.
Referenced by build_().

Func PLearn::TangentLearner::tangent_predictor

Definition at line 95 of file TangentLearner.h.
Referenced by build_(), and makeDeepCopyFromShallowCopy().

Var PLearn::TangentLearner::tangent_targets [protected]

Definition at line 66 of file TangentLearner.h.
Referenced by build_(), and makeDeepCopyFromShallowCopy().

string PLearn::TangentLearner::training_targets

Definition at line 83 of file TangentLearner.h.
Referenced by build_(), and train().

bool PLearn::TangentLearner::use_subspace_distance

Definition at line 84 of file TangentLearner.h.
Referenced by build_().

Var PLearn::TangentLearner::V [protected]

Definition at line 65 of file TangentLearner.h.
Referenced by build_(), initializeParams(), and makeDeepCopyFromShallowCopy().

Var PLearn::TangentLearner::W [protected]

Definition at line 65 of file TangentLearner.h.
Referenced by build_(), initializeParams(), and makeDeepCopyFromShallowCopy().

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

Generated on Tue Aug 17 16:28:01 2004 for PLearn by

1.3.7

PLearn::TangentLearner Class Reference

Public Member Functions

Public Attributes

Static Protected Member Functions

Protected Attributes

Private Types

Private Member Functions

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation