PLearn::NeighborhoodSmoothnessNNet Class Reference

#include <NeighborhoodSmoothnessNNet.h>

Inheritance diagram for PLearn::NeighborhoodSmoothnessNNet:

[legend]Collaboration diagram for PLearn::NeighborhoodSmoothnessNNet:

[legend]List of all members.


Public Types
typedef PLearner	inherited
Public Member Functions
	NeighborhoodSmoothnessNNet ()
virtual	~NeighborhoodSmoothnessNNet ()
	PLEARN_DECLARE_OBJECT (NeighborhoodSmoothnessNNet)
virtual void	build ()
	** SUBCLASS WRITING: ** This method should be redefined in subclasses, to just call inherited::build() and then build_()
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 int	outputsize () const
	SUBCLASS WRITING: overload this so that it returns the size of this learner's output, as a function of its inputsize(), targetsize() and set options.
virtual TVec< string >	getTrainCostNames () const
	* SUBCLASS WRITING: * This should return the names of the objective costs that the train method computes and for which it updates the VecStatsCollector train_stats
virtual TVec< string >	getTestCostNames () const
	* SUBCLASS WRITING: * This should return the names of the costs computed by computeCostsFromOutpus
virtual void	train ()
	The role of the train method is to bring the learner up to stage==nstages, updating the stats with training costs measured on-line in the process.
virtual void	setTrainingSet (VMat training_set, bool call_forget=true)
	Declares the train_set Then calls build() and forget() if necessary Note: You shouldn't have to overload this in subclasses, except in maybe to forward the call to an underlying learner.
virtual void	computeOutput (const Vec &input, Vec &output) const
	* SUBCLASS WRITING: * This should be defined in subclasses to compute the output from the input
virtual void	computeOutputAndCosts (const Vec &input, const Vec &target, Vec &output, Vec &costs) const
	Default calls computeOutput and computeCostsFromOutputs You may overload this if you have a more efficient way to compute both output and weighted costs at the same time.
virtual void	computeCostsFromOutputs (const Vec &input, const Vec &output, const Vec &target, Vec &costs) const
	* SUBCLASS WRITING: * This should be defined in subclasses to compute the weighted costs from already computed output.
virtual void	makeDeepCopyFromShallowCopy (CopiesMap &copies)
Public Attributes
Func	f
Func	f_input_to_hidden
Func	test_costf
Func	output_and_target_to_cost
int	max_n_instances
int	nhidden
int	nhidden2
int	noutputs
real	sigma_hidden
real	sne_weight
real	weight_decay
real	bias_decay
real	layer1_weight_decay
real	layer1_bias_decay
real	layer2_weight_decay
real	layer2_bias_decay
real	output_layer_weight_decay
real	output_layer_bias_decay
real	direct_in_to_out_weight_decay
real	classification_regularizer
bool	L1_penalty
bool	direct_in_to_out
string	output_transfer_func
real	interval_minval
real	interval_maxval
Array< string >	cost_funcs
	a list of cost functions to use in the form "[ cf1; cf2; cf3; ... ]"
PP< Optimizer >	optimizer
int	batch_size
Protected Member Functions
void	initializeParams ()
Static Protected Member Functions
void	declareOptions (OptionList &ol)
	redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options) ( see the declareOption function further down)
Protected Attributes
Var	input
Var	target
Var	sampleweight
Var	w1
Var	w2
Var	wout
Var	wdirect
Var	last_hidden
Var	output
Var	bag_size
Var	bag_inputs
Var	bag_output
Var	bag_hidden
int	test_bag_size
Func	invars_to_training_cost
VarArray	costs
VarArray	penalties
Var	training_cost
Var	test_costs
VarArray	invars
VarArray	params
Vec	paramsvalues
Var	p_ij
Private Member Functions
void	build_ ()

Member Typedef Documentation

typedef PLearner PLearn::NeighborhoodSmoothnessNNet::inherited

Reimplemented from PLearn::PLearner.
Definition at line 93 of file NeighborhoodSmoothnessNNet.h.

Constructor & Destructor Documentation

PLearn::NeighborhoodSmoothnessNNet::NeighborhoodSmoothnessNNet ( )

Definition at line 97 of file NeighborhoodSmoothnessNNet.cc.

PLearn::NeighborhoodSmoothnessNNet::~NeighborhoodSmoothnessNNet ( ) [virtual]

Definition at line 122 of file NeighborhoodSmoothnessNNet.cc.

Member Function Documentation

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

**** SUBCLASS WRITING: **** This method should be redefined in subclasses, to just call inherited::build() and then build_()

Reimplemented from PLearn::PLearner.
Definition at line 227 of file NeighborhoodSmoothnessNNet.cc.
References build_().
Referenced by setTrainingSet(), and train().

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

**** SUBCLASS WRITING: **** This method should finalize building of the object, according to set 'options', in *any* situation.
Typical situations include:

Initial building of an object from a few user-specified options
Building of a "reloaded" object: i.e. from the complete set of all serialised options.
Updating or "re-building" of an object after a few "tuning" options (such as hyper-parameters) have been modified.

You can assume that the parent class' build_() has already been called.
A typical build method will want to know the inputsize(), targetsize() and outputsize(), and may also want to check whether train_set->hasWeights(). All these methods require a train_set to be set, so the first thing you may want to do, is check if(train_set), before doing any heavy building...
Note: build() is always called by setTrainingSet.
Reimplemented from PLearn::PLearner.
Definition at line 236 of file NeighborhoodSmoothnessNNet.cc.
References PLearn::affine_transform(), PLearn::affine_transform_weight_penalty(), PLearn::TVec< Var >::append(), bag_hidden, bag_inputs, bag_size, bias_decay, PLearn::binary_classification_loss(), c_str(), PLearn::classification_loss(), classification_regularizer, cost_funcs, costs, PLearn::cross_entropy(), direct_in_to_out, direct_in_to_out_weight_decay, PLearn::dot(), PLearn::exp(), f, f_input_to_hidden, PLearn::hconcat(), initializeParams(), input, PLearn::PLearner::inputsize(), interval_maxval, interval_minval, invars, invars_to_training_cost, PLearn::invertElements(), PLearn::TVec< Var >::isNull(), k, L1_penalty, last_hidden, layer1_bias_decay, layer1_weight_decay, layer2_bias_decay, layer2_weight_decay, PLearn::Var::length(), PLearn::lift_output(), PLearn::log(), PLearn::log_softmax(), PLearn::VarArray::makeSharedValue(), max_n_instances, PLearn::minus(), PLearn::multiclass_loss(), PLearn::neg_log_pi(), PLearn::VarArray::nelems(), PLearn::newObject(), nhidden, nhidden2, PLearn::onehot_squared_loss(), output, output_and_target_to_cost, output_layer_bias_decay, output_layer_weight_decay, output_transfer_func, outputsize(), p_ij, params, paramsvalues, penalties, PLERROR, PLearn::TVec< Var >::push_back(), PLearn::TVec< T >::resize(), PLearn::TVec< Var >::resize(), sampleweight, sigma_hidden, PLearn::sigmoid(), PLearn::TVec< Var >::size(), PLearn::TVec< string >::size(), PLearn::TVec< T >::size(), sne_weight, PLearn::softmax(), PLearn::softplus(), PLearn::stable_cross_entropy(), PLearn::subMat(), PLearn::sum(), PLearn::sumabs(), PLearn::sumsquare(), PLearn::tanh(), target, PLearn::PLearner::targetsize(), test_costf, test_costs, PLearn::times(), PLearn::timesScalar(), training_cost, PLearn::transposeProduct(), PLearn::unfoldedFunc(), PLearn::var(), w1, w2, wdirect, weight_decay, PLearn::Var::width(), and wout.
Referenced by build().

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

const Vec & output,

const Vec & target,

Vec & costs

) const [virtual]

*** SUBCLASS WRITING: *** This should be defined in subclasses to compute the weighted costs from already computed output.
The costs should correspond to the cost names returned by getTestCostNames() NOTE: In exotic cases, the cost may also depend on some info in the input, that's why the method also gets so see it.
Implements PLearn::PLearner.
Definition at line 691 of file NeighborhoodSmoothnessNNet.cc.
References output_and_target_to_cost.

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

Vec & output

) const [virtual]

*** SUBCLASS WRITING: *** This should be defined in subclasses to compute the output from the input

Implements PLearn::PLearner.
Definition at line 673 of file NeighborhoodSmoothnessNNet.cc.
References f.

void PLearn::NeighborhoodSmoothnessNNet::computeOutputAndCosts ( const Vec & input,

const Vec & target,

Vec & output,

Vec & costs

) const [virtual]

Default calls computeOutput and computeCostsFromOutputs You may overload this if you have a more efficient way to compute both output and weighted costs at the same time.

Reimplemented from PLearn::PLearner.
Definition at line 682 of file NeighborhoodSmoothnessNNet.cc.
References test_costf.

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

redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options) ( see the declareOption function further down)
ex: static void declareOptions(OptionList& ol) { declareOption(ol, "inputsize", &MyObject::inputsize_, OptionBase::buildoption, "the size of the input\n it must be provided"); declareOption(ol, "weights", &MyObject::weights, OptionBase::learntoption, "the learnt model weights"); inherited::declareOptions(ol); }
Reimplemented from PLearn::PLearner.
Definition at line 126 of file NeighborhoodSmoothnessNNet.cc.
References PLearn::declareOption(), and PLearn::OptionList.

void PLearn::NeighborhoodSmoothnessNNet::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!)
*** SUBCLASS WRITING: *** A typical forget() method should do the following:

initialize a random number generator with the seed option
initialize the learner's parameters, using this random generator
stage = 0; This method is typically called by the build_() method, after it has finished setting up the parameters, and if it deemed useful to set or reset the learner in its fresh state. (remember build may be called after modifying options that do not necessarily require the learner to restart from a fresh state...) forget is also called by the setTrainingSet method, after calling build(), so it will generally be called TWICE during setTrainingSet!

Implements PLearn::PLearner.
Definition at line 751 of file NeighborhoodSmoothnessNNet.cc.
References initializeParams().
Referenced by setTrainingSet().

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

*** SUBCLASS WRITING: *** This should return the names of the costs computed by computeCostsFromOutpus

Implements PLearn::PLearner.
Definition at line 544 of file NeighborhoodSmoothnessNNet.cc.
References cost_funcs.

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

*** SUBCLASS WRITING: *** This should return 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 536 of file NeighborhoodSmoothnessNNet.cc.
References cost_funcs.

void PLearn::NeighborhoodSmoothnessNNet::initializeParams ( ) [protected]

Definition at line 700 of file NeighborhoodSmoothnessNNet.cc.
References direct_in_to_out, PLearn::fill_random_normal(), PLearn::PLearner::inputsize(), PLearn::manual_seed(), nhidden, nhidden2, optimizer, PLearn::seed(), w1, w2, wdirect, and wout.
Referenced by build_(), and forget().

void PLearn::NeighborhoodSmoothnessNNet::makeDeepCopyFromShallowCopy ( CopiesMap & copies ) [virtual]

Does the necessary operations to transform a shallow copy (this) into a deep copy by deep-copying all the members that need to be. Typical implementation:
void CLASS_OF_THIS::makeDeepCopyFromShallowCopy(CopiesMap& copies) { SUPERCLASS_OF_THIS::makeDeepCopyFromShallowCopy(copies); member_ptr = member_ptr->deepCopy(copies); member_smartptr = member_smartptr->deepCopy(copies); member_mat.makeDeepCopyFromShallowCopy(copies); member_vec.makeDeepCopyFromShallowCopy(copies); ... }
Reimplemented from PLearn::PLearner.
Definition at line 760 of file NeighborhoodSmoothnessNNet.cc.
References bag_hidden, bag_inputs, bag_output, bag_size, PLearn::CopiesMap, cost_funcs, costs, PLearn::deepCopyField(), f, f_input_to_hidden, input, invars, invars_to_training_cost, last_hidden, optimizer, output, output_and_target_to_cost, p_ij, params, paramsvalues, penalties, sampleweight, target, test_costf, test_costs, training_cost, w1, w2, wdirect, and wout.

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

SUBCLASS WRITING: overload this so that it returns the size of this learner's output, as a function of its inputsize(), targetsize() and set options.

Implements PLearn::PLearner.
Definition at line 530 of file NeighborhoodSmoothnessNNet.cc.
References noutputs.
Referenced by build_().

PLearn::NeighborhoodSmoothnessNNet::PLEARN_DECLARE_OBJECT ( NeighborhoodSmoothnessNNet )

void PLearn::NeighborhoodSmoothnessNNet::setTrainingSet ( VMat training_set,

bool call_forget = true

) [virtual]

Declares the train_set Then calls build() and forget() if necessary Note: You shouldn't have to overload this in subclasses, except in maybe to forward the call to an underlying learner.

Reimplemented from PLearn::PLearner.
Definition at line 549 of file NeighborhoodSmoothnessNNet.cc.
References build(), forget(), PLearn::VMat::length(), PLERROR, and PLearn::VMat::width().

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

The role of the train method is to bring the learner up to stage==nstages, updating the stats with training costs measured on-line in the process.
*** SUBCLASS WRITING: ***
TYPICAL CODE:
static Vec input; // static so we don't reallocate/deallocate memory each time... static Vec target; // (but be careful that static means shared!) input.resize(inputsize()); // the train_set's inputsize() target.resize(targetsize()); // the train_set's targetsize() real weight;
if(!train_stats) // make a default stats collector, in case there's none train_stats = new VecStatsCollector();
if(nstages<stage) // asking to revert to a previous stage! forget(); // reset the learner to stage=0
while(stage<nstages) { clear statistics of previous epoch train_stats->forget();
... train for 1 stage, and update train_stats, using train_set->getSample(input, target, weight); and train_stats->update(train_costs)
++stage; train_stats->finalize(); // finalize statistics for this epoch }
Implements PLearn::PLearner.
Definition at line 579 of file NeighborhoodSmoothnessNNet.cc.
References batch_size, build(), PLearn::endl(), f, invars_to_training_cost, PLearn::PP< Function >::isNull(), PLearn::VMat::length(), max_n_instances, optimizer, output_and_target_to_cost, params, PLERROR, PLearn::sumOverBags(), test_costf, PLearn::tostring(), PLearn::ProgressBar::update(), and PLearn::VMat::width().