PLearn 0.1
Public Member Functions | Static Public Member Functions | Public Attributes | Static Public Attributes | Static Protected Member Functions | Private Types | Private Member Functions
PLearn::NaryVariable Class Reference

#include <NaryVariable.h>

Inheritance diagram for PLearn::NaryVariable:
Inheritance graph
[legend]
Collaboration diagram for PLearn::NaryVariable:
Collaboration graph
[legend]

List of all members.

Public Member Functions

 NaryVariable ()
 NaryVariable (const VarArray &the_varray, int thelength, int thewidth=1, bool call_build_=true)
virtual NaryVariabledeepCopy (CopiesMap &copies) const
virtual void makeDeepCopyFromShallowCopy (CopiesMap &copies)
 Does the necessary operations to transform a shallow copy (this) into a deep copy by deep-copying all the members that need to be.
virtual void build ()
 Post-constructor.
virtual void setParents (const VarArray &parents)
 set this Variable's parents. To use with default constructor.
virtual bool markPath ()
 Sets the marked flag of all the sVariable that are to be in the fprop path.
virtual void buildPath (VarArray &proppath)
 Finally buildPath is to be called from the output Variable of interest (this will build the proppath at the same time as erasing the marks)
virtual VarArray sources ()
 if not marked, find all constant sources that influence this Variable.
virtual VarArray random_sources ()
 return ancestors which compute a non-deterministic function of their parents
virtual VarArray ancestors ()
 if not marked, find all Variables that influence this Variable.
virtual void unmarkAncestors ()
 undo any marking done by a call to sources() or ancestors()
virtual VarArray parents ()
 returns all the direct parents of this Var that are not marked (the call doesn't change any mark)
void printInfo (bool print_gradient)
virtual void resizeRValue ()

Static Public Member Functions

static string _classname_ ()
 NaryVariable.
static OptionList_getOptionList_ ()
static RemoteMethodMap_getRemoteMethodMap_ ()
static bool _isa_ (const Object *o)
static void _static_initialize_ ()
static const PPathdeclaringFile ()

Public Attributes

VarArray varray

Static Public Attributes

static StaticInitializer _static_initializer_

Static Protected Member Functions

static void declareOptions (OptionList &ol)
 Default constructor for persistence.

Private Types

typedef Variable inherited

Private Member Functions

void build_ ()
 Object-specific post-constructor.

Detailed Description

Definition at line 59 of file NaryVariable.h.


Member Typedef Documentation


Constructor & Destructor Documentation

PLearn::NaryVariable::NaryVariable ( ) [inline]

Definition at line 71 of file NaryVariable.h.

{}
PLearn::NaryVariable::NaryVariable ( const VarArray the_varray,
int  thelength,
int  thewidth = 1,
bool  call_build_ = true 
)

Definition at line 58 of file NaryVariable.cc.

References build_().

                                                          :
    inherited(thelength, thewidth, call_build_),
    varray(the_varray)
{
    if (call_build_)
        build_();
}

Here is the call graph for this function:


Member Function Documentation

string PLearn::NaryVariable::_classname_ ( ) [static]
OptionList & PLearn::NaryVariable::_getOptionList_ ( ) [static]
RemoteMethodMap & PLearn::NaryVariable::_getRemoteMethodMap_ ( ) [static]
bool PLearn::NaryVariable::_isa_ ( const Object o) [static]
StaticInitializer NaryVariable::_static_initializer_ & PLearn::NaryVariable::_static_initialize_ ( ) [static]
VarArray PLearn::NaryVariable::ancestors ( ) [virtual]

if not marked, find all Variables that influence this Variable.

Implements PLearn::Variable.

Definition at line 165 of file NaryVariable.cc.

References a, i, PLearn::Variable::marked, PLearn::TVec< T >::size(), PLearn::Variable::Var, and varray.

{ 
    VarArray a(0,0);
    if (marked)
        return a;
    marked = true;
    for(int i=0; i<varray.size(); i++)
        if (!varray[i].isNull())
            a &= varray[i]->ancestors();
    a &= Var(this);
    return a;
}

Here is the call graph for this function:

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

Post-constructor.

The normal implementation should call simply inherited::build(), then this class's build_(). This method should be callable again at later times, after modifying some option fields to change the "architecture" of the object.

Reimplemented from PLearn::Variable.

Reimplemented in PLearn::BiasWeightAffineTransformVariable, PLearn::CCCostVariable, PLearn::ConcatColumnsVariable, PLearn::ConcatOfVariable, PLearn::ConcatRowsVariable, PLearn::ConfRatedAdaboostCostVariable, PLearn::DiagonalizedFactorsProductVariable, PLearn::DoubleProductVariable, PLearn::LinearCombinationOfScalarVariables, PLearn::TransposedDoubleProductVariable, PLearn::FNetLayerVariable, PLearn::GaussianProcessNLLVariable, PLearn::HeterogenuousAffineTransformVariable, PLearn::HeterogenuousAffineTransformWeightPenalty, PLearn::IfThenElseVariable, PLearn::LocalizedFeaturesLayerVariable, PLearn::MatrixElementsVariable, PLearn::MatrixSumOfVariable, PLearn::NegLogPoissonVariable, PLearn::NllGeneralGaussianVariable, PLearn::NllSemisphericalGaussianVariable, PLearn::PlusManyVariable, PLearn::PotentialsVariable, PLearn::SemiSupervisedProbClassCostVariable, PLearn::SumOfVariable, PLearn::SumOverBagsVariable, PLearn::UnfoldedFuncVariable, PLearn::UnfoldedSumOfVariable, PLearn::VarArrayElementVariable, PLearn::ScoreLayerVariable, and PLearn::WeightedLogGaussian.

Definition at line 81 of file NaryVariable.cc.

References PLearn::Variable::build(), and build_().

Referenced by PLearn::WeightedLogGaussian::build(), PLearn::VarArrayElementVariable::build(), PLearn::UnfoldedSumOfVariable::build(), PLearn::UnfoldedFuncVariable::build(), PLearn::TransposedDoubleProductVariable::build(), PLearn::SumOverBagsVariable::build(), PLearn::SumOfVariable::build(), PLearn::SemiSupervisedProbClassCostVariable::build(), PLearn::ScoreLayerVariable::build(), PLearn::PotentialsVariable::build(), PLearn::PlusManyVariable::build(), PLearn::NllSemisphericalGaussianVariable::build(), PLearn::NllGeneralGaussianVariable::build(), PLearn::NegLogPoissonVariable::build(), PLearn::MatrixSumOfVariable::build(), PLearn::MatrixElementsVariable::build(), PLearn::LocalizedFeaturesLayerVariable::build(), PLearn::LinearCombinationOfScalarVariables::build(), PLearn::IfThenElseVariable::build(), PLearn::HeterogenuousAffineTransformWeightPenalty::build(), PLearn::HeterogenuousAffineTransformVariable::build(), PLearn::GaussianProcessNLLVariable::build(), PLearn::FNetLayerVariable::build(), PLearn::DoubleProductVariable::build(), PLearn::DiagonalizedFactorsProductVariable::build(), PLearn::ConfRatedAdaboostCostVariable::build(), PLearn::ConcatRowsVariable::build(), PLearn::ConcatOfVariable::build(), PLearn::ConcatColumnsVariable::build(), PLearn::CCCostVariable::build(), PLearn::BiasWeightAffineTransformVariable::build(), PLearn::UnfoldedFuncVariable::build_(), PLearn::SumOverBagsVariable::build_(), PLearn::SumOfVariable::build_(), PLearn::ScoreLayerVariable::build_(), and PLearn::NNet::buildOutputFromInput().

Here is the call graph for this function:

Here is the caller graph for this function:

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

Object-specific post-constructor.

This method should be redefined in subclasses and do the actual building of the object according to previously set option fields. Constructors can just set option fields, and then call build_. This method is NOT virtual, and will typically be called only from three places: a constructor, the public virtual build() method, and possibly the public virtual read method (which calls its parent's read). build_() can assume that its parent's build_() has already been called.

Reimplemented from PLearn::Variable.

Reimplemented in PLearn::BiasWeightAffineTransformVariable, PLearn::CCCostVariable, PLearn::ConcatColumnsVariable, PLearn::ConcatOfVariable, PLearn::ConcatRowsVariable, PLearn::ConfRatedAdaboostCostVariable, PLearn::DiagonalizedFactorsProductVariable, PLearn::DoubleProductVariable, PLearn::LinearCombinationOfScalarVariables, PLearn::TransposedDoubleProductVariable, PLearn::FNetLayerVariable, PLearn::GaussianProcessNLLVariable, PLearn::HeterogenuousAffineTransformVariable, PLearn::HeterogenuousAffineTransformWeightPenalty, PLearn::IfThenElseVariable, PLearn::LocalizedFeaturesLayerVariable, PLearn::MatrixElementsVariable, PLearn::MatrixSumOfVariable, PLearn::NegLogPoissonVariable, PLearn::NllGeneralGaussianVariable, PLearn::NllSemisphericalGaussianVariable, PLearn::PlusManyVariable, PLearn::PotentialsVariable, PLearn::SemiSupervisedProbClassCostVariable, PLearn::SumOfVariable, PLearn::SumOverBagsVariable, PLearn::UnfoldedFuncVariable, PLearn::UnfoldedSumOfVariable, PLearn::VarArrayElementVariable, PLearn::ScoreLayerVariable, and PLearn::WeightedLogGaussian.

Definition at line 90 of file NaryVariable.cc.

Referenced by build(), and NaryVariable().

{
    // Nothing to do here.
}

Here is the caller graph for this function:

void PLearn::NaryVariable::buildPath ( VarArray proppath) [virtual]

Finally buildPath is to be called from the output Variable of interest (this will build the proppath at the same time as erasing the marks)

Implements PLearn::Variable.

Definition at line 122 of file NaryVariable.cc.

References PLearn::Variable::clearMark(), i, PLearn::Variable::marked, PLearn::TVec< T >::size(), PLearn::Variable::Var, and varray.

{
    if(marked)
    {
        for(int i=0; i<varray.size(); i++)
            if (!varray[i].isNull())
                varray[i]->buildPath(proppath);
        proppath &= Var(this);
        clearMark();
    }
}

Here is the call graph for this function:

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

Default constructor for persistence.

Reimplemented from PLearn::Variable.

Reimplemented in PLearn::CCCostVariable, PLearn::ConcatOfVariable, PLearn::ConfRatedAdaboostCostVariable, PLearn::DoubleProductVariable, PLearn::LinearCombinationOfScalarVariables, PLearn::TransposedDoubleProductVariable, PLearn::FNetLayerVariable, PLearn::GaussianProcessNLLVariable, PLearn::HeterogenuousAffineTransformVariable, PLearn::HeterogenuousAffineTransformWeightPenalty, PLearn::LocalizedFeaturesLayerVariable, PLearn::MatrixElementsVariable, PLearn::MatrixSumOfVariable, PLearn::PlusManyVariable, PLearn::PotentialsVariable, PLearn::SemiSupervisedProbClassCostVariable, PLearn::SoftSlopeIntegralVariable, PLearn::SoftSlopeVariable, PLearn::SumOfVariable, PLearn::SumOverBagsVariable, PLearn::UnfoldedFuncVariable, PLearn::UnfoldedSumOfVariable, and PLearn::ScoreLayerVariable.

Definition at line 70 of file NaryVariable.cc.

References PLearn::OptionBase::buildoption, PLearn::declareOption(), PLearn::Variable::declareOptions(), and varray.

Referenced by PLearn::UnfoldedSumOfVariable::declareOptions(), PLearn::UnfoldedFuncVariable::declareOptions(), PLearn::TransposedDoubleProductVariable::declareOptions(), PLearn::SumOverBagsVariable::declareOptions(), PLearn::SumOfVariable::declareOptions(), PLearn::SoftSlopeVariable::declareOptions(), PLearn::SoftSlopeIntegralVariable::declareOptions(), PLearn::SemiSupervisedProbClassCostVariable::declareOptions(), PLearn::ScoreLayerVariable::declareOptions(), PLearn::PotentialsVariable::declareOptions(), PLearn::PlusManyVariable::declareOptions(), PLearn::MatrixSumOfVariable::declareOptions(), PLearn::MatrixElementsVariable::declareOptions(), PLearn::LocalizedFeaturesLayerVariable::declareOptions(), PLearn::LinearCombinationOfScalarVariables::declareOptions(), PLearn::HeterogenuousAffineTransformWeightPenalty::declareOptions(), PLearn::HeterogenuousAffineTransformVariable::declareOptions(), PLearn::GaussianProcessNLLVariable::declareOptions(), PLearn::FNetLayerVariable::declareOptions(), PLearn::DoubleProductVariable::declareOptions(), PLearn::ConcatOfVariable::declareOptions(), and PLearn::CCCostVariable::declareOptions().

{
    declareOption(ol, "varray", &NaryVariable::varray, OptionBase::buildoption, 
                  "The array of parent variables that this one depends on.");

    inherited::declareOptions(ol);
}

Here is the call graph for this function:

Here is the caller graph for this function:

static const PPath& PLearn::NaryVariable::declaringFile ( ) [inline, static]
NaryVariable * PLearn::NaryVariable::deepCopy ( CopiesMap copies) const [virtual]
void PLearn::NaryVariable::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.

This needs to be overridden by every class that adds "complex" data members to the class, such as Vec, Mat, PP<Something>, etc. Typical implementation:

  void CLASS_OF_THIS::makeDeepCopyFromShallowCopy(CopiesMap& copies)
  {
      inherited::makeDeepCopyFromShallowCopy(copies);
      deepCopyField(complex_data_member1, copies);
      deepCopyField(complex_data_member2, copies);
      ...
  }
Parameters:
copiesA map used by the deep-copy mechanism to keep track of already-copied objects.

Reimplemented from PLearn::Variable.

Reimplemented in PLearn::ArgminOfVariable, PLearn::BiasWeightAffineTransformVariable, PLearn::CCCostVariable, PLearn::ConcatOfVariable, PLearn::DoubleProductVariable, PLearn::LinearCombinationOfScalarVariables, PLearn::TransposedDoubleProductVariable, PLearn::FNetLayerVariable, PLearn::GaussianProcessNLLVariable, PLearn::HeterogenuousAffineTransformVariable, PLearn::HeterogenuousAffineTransformWeightPenalty, PLearn::LocalizedFeaturesLayerVariable, PLearn::MatrixElementsVariable, PLearn::MatrixSumOfVariable, PLearn::NllGeneralGaussianVariable, PLearn::PlusManyVariable, PLearn::PotentialsVariable, PLearn::SumOfVariable, PLearn::SumOverBagsVariable, PLearn::UnfoldedFuncVariable, PLearn::UnfoldedSumOfVariable, and PLearn::ScoreLayerVariable.

Definition at line 98 of file NaryVariable.cc.

References PLearn::deepCopyField(), PLearn::Variable::makeDeepCopyFromShallowCopy(), and varray.

Referenced by PLearn::UnfoldedSumOfVariable::makeDeepCopyFromShallowCopy(), PLearn::UnfoldedFuncVariable::makeDeepCopyFromShallowCopy(), PLearn::TransposedDoubleProductVariable::makeDeepCopyFromShallowCopy(), PLearn::SumOverBagsVariable::makeDeepCopyFromShallowCopy(), PLearn::SumOfVariable::makeDeepCopyFromShallowCopy(), PLearn::ScoreLayerVariable::makeDeepCopyFromShallowCopy(), PLearn::PotentialsVariable::makeDeepCopyFromShallowCopy(), PLearn::PlusManyVariable::makeDeepCopyFromShallowCopy(), PLearn::MatrixSumOfVariable::makeDeepCopyFromShallowCopy(), PLearn::MatrixElementsVariable::makeDeepCopyFromShallowCopy(), PLearn::LocalizedFeaturesLayerVariable::makeDeepCopyFromShallowCopy(), PLearn::LinearCombinationOfScalarVariables::makeDeepCopyFromShallowCopy(), PLearn::HeterogenuousAffineTransformWeightPenalty::makeDeepCopyFromShallowCopy(), PLearn::HeterogenuousAffineTransformVariable::makeDeepCopyFromShallowCopy(), PLearn::GaussianProcessNLLVariable::makeDeepCopyFromShallowCopy(), PLearn::FNetLayerVariable::makeDeepCopyFromShallowCopy(), PLearn::DoubleProductVariable::makeDeepCopyFromShallowCopy(), PLearn::ConcatOfVariable::makeDeepCopyFromShallowCopy(), PLearn::CCCostVariable::makeDeepCopyFromShallowCopy(), PLearn::BiasWeightAffineTransformVariable::makeDeepCopyFromShallowCopy(), and PLearn::ArgminOfVariable::makeDeepCopyFromShallowCopy().

Here is the call graph for this function:

Here is the caller graph for this function:

bool PLearn::NaryVariable::markPath ( ) [virtual]

Sets the marked flag of all the sVariable that are to be in the fprop path.

The input sVariable that are of interest are to be marked first. Then markPath is to be called from the output Variable of interest

Implements PLearn::Variable.

Definition at line 110 of file NaryVariable.cc.

References i, PLearn::Variable::marked, PLearn::TVec< T >::size(), and varray.

{
    if(!marked)
    {
        for(int i=0; i<varray.size(); i++)
            if (!varray[i].isNull())
                marked |= varray[i]->markPath();
    }
    return marked;
}

Here is the call graph for this function:

VarArray PLearn::NaryVariable::parents ( ) [virtual]

returns all the direct parents of this Var that are not marked (the call doesn't change any mark)

Implements PLearn::Variable.

Definition at line 191 of file NaryVariable.cc.

References PLearn::TVec< T >::append(), i, PLearn::TVec< T >::size(), and varray.

Referenced by setParents().

{
    VarArray unmarked_parents;
    for(int i=0; i<varray.size(); i++)
        if (!varray[i].isNull() && !varray[i]->marked)
            unmarked_parents.append(varray[i]);
    return unmarked_parents;
}

Here is the call graph for this function:

Here is the caller graph for this function:

void PLearn::NaryVariable::printInfo ( bool  print_gradient) [inline, virtual]

Implements PLearn::Variable.

Reimplemented in PLearn::CCCostVariable, PLearn::MatrixSumOfVariable, PLearn::SumOfVariable, PLearn::SumOverBagsVariable, PLearn::UnfoldedFuncVariable, and PLearn::UnfoldedSumOfVariable.

Definition at line 91 of file NaryVariable.h.

References PLearn::endl(), i, and PLearn::pout.

                                        { 
        pout <<  getName() << "[" << (void*)this << "] " << classname() << "(" << (void*)varray[0];
        for (int i=1;i<varray.size();i++)
            pout << "," << (void*)varray[i];
        pout << ") = " << value;
        if (print_gradient) pout << " gradient=" << gradient;
        pout << endl; 
    }

Here is the call graph for this function:

VarArray PLearn::NaryVariable::random_sources ( ) [virtual]

return ancestors which compute a non-deterministic function of their parents

Implements PLearn::Variable.

Definition at line 151 of file NaryVariable.cc.

References a, i, PLearn::Variable::marked, PLearn::TVec< T >::size(), and varray.

{
    VarArray a(0,0);
    if (!marked)
    {
        marked = true;
        for(int i=0; i<varray.size(); i++)
            if (!varray[i].isNull())
                a &= varray[i]->random_sources();
    }
    return a;
}

Here is the call graph for this function:

void PLearn::NaryVariable::resizeRValue ( ) [virtual]

Reimplemented from PLearn::Variable.

Definition at line 201 of file NaryVariable.cc.

References i, PLearn::VarArray::resizeRValue(), PLearn::Variable::resizeRValue(), PLearn::Variable::rvaluedata, PLearn::TVec< T >::size(), and varray.

Referenced by PLearn::SumOfVariable::rfprop(), PLearn::IfThenElseVariable::rfprop(), and PLearn::ConcatRowsVariable::rfprop().

{
    inherited::resizeRValue();
    for (int i=0; i<varray.size(); i++)
        if (!varray[i]->rvaluedata) varray[i]->resizeRValue();
}

Here is the call graph for this function:

Here is the caller graph for this function:

void PLearn::NaryVariable::setParents ( const VarArray parents) [virtual]

set this Variable's parents. To use with default constructor.

Reimplemented from PLearn::Variable.

Definition at line 104 of file NaryVariable.cc.

References parents(), PLearn::Variable::sizeprop(), and varray.

Here is the call graph for this function:

VarArray PLearn::NaryVariable::sources ( ) [virtual]

if not marked, find all constant sources that influence this Variable.

A constant source is normally a SourceVariable.

Implements PLearn::Variable.

Definition at line 135 of file NaryVariable.cc.

References a, i, PLearn::Variable::marked, PLearn::TVec< T >::size(), and varray.

{
    VarArray a(0,0);
    if (!marked)
    {
        marked = true;
        for(int i=0; i<varray.size(); i++)
            if (!varray[i].isNull())
                a &= varray[i]->sources();
        //if (a.size()==0)
        //    a &= Var(this);
    }
    return a;
}

Here is the call graph for this function:

void PLearn::NaryVariable::unmarkAncestors ( ) [virtual]

undo any marking done by a call to sources() or ancestors()

Implements PLearn::Variable.

Definition at line 179 of file NaryVariable.cc.

References i, PLearn::Variable::marked, PLearn::TVec< T >::size(), and varray.

{
    if (marked)
    {
        marked = false;
        for(int i=0; i<varray.size(); i++)
            if (!varray[i].isNull())
                varray[i]->unmarkAncestors();
    }
}

Here is the call graph for this function:


Member Data Documentation

Definition at line 66 of file NaryVariable.h.

Referenced by ancestors(), PLearn::VarArrayElementVariable::bprop(), PLearn::SoftSlopeVariable::bprop(), PLearn::SoftSlopeIntegralVariable::bprop(), PLearn::PlusManyVariable::bprop(), PLearn::NllSemisphericalGaussianVariable::bprop(), PLearn::NllGeneralGaussianVariable::bprop(), PLearn::NegLogPoissonVariable::bprop(), PLearn::LocalizedFeaturesLayerVariable::bprop(), PLearn::LinearCombinationOfScalarVariables::bprop(), PLearn::HeterogenuousAffineTransformWeightPenalty::bprop(), PLearn::HeterogenuousAffineTransformVariable::bprop(), PLearn::HardSlopeVariable::bprop(), PLearn::FNetLayerVariable::bprop(), PLearn::DoubleProductVariable::bprop(), PLearn::ConfRatedAdaboostCostVariable::bprop(), PLearn::ConcatRowsVariable::bprop(), PLearn::ConcatColumnsVariable::bprop(), PLearn::VarArrayElementVariable::build_(), PLearn::UnfoldedFuncVariable::build_(), PLearn::SumOverBagsVariable::build_(), PLearn::SumOfVariable::build_(), PLearn::SemiSupervisedProbClassCostVariable::build_(), PLearn::ScoreLayerVariable::build_(), PLearn::PlusManyVariable::build_(), PLearn::NllSemisphericalGaussianVariable::build_(), PLearn::NllGeneralGaussianVariable::build_(), PLearn::NegLogPoissonVariable::build_(), PLearn::LocalizedFeaturesLayerVariable::build_(), PLearn::IfThenElseVariable::build_(), PLearn::HeterogenuousAffineTransformWeightPenalty::build_(), PLearn::HeterogenuousAffineTransformVariable::build_(), PLearn::FNetLayerVariable::build_(), PLearn::DiagonalizedFactorsProductVariable::build_(), PLearn::ConfRatedAdaboostCostVariable::build_(), PLearn::ConcatRowsVariable::build_(), PLearn::ConcatColumnsVariable::build_(), PLearn::BiasWeightAffineTransformVariable::build_(), PLearn::NNet::buildOutputFromInput(), buildPath(), PLearn::LocalizedFeaturesLayerVariable::computeSubsets(), PLearn::UnfoldedFuncVariable::declareOptions(), PLearn::ScoreLayerVariable::declareOptions(), declareOptions(), PLearn::VarArrayElementVariable::fprop(), PLearn::SoftSlopeVariable::fprop(), PLearn::SoftSlopeIntegralVariable::fprop(), PLearn::PlusManyVariable::fprop(), PLearn::NegLogPoissonVariable::fprop(), PLearn::LocalizedFeaturesLayerVariable::fprop(), PLearn::LinearCombinationOfScalarVariables::fprop(), PLearn::HeterogenuousAffineTransformWeightPenalty::fprop(), PLearn::HeterogenuousAffineTransformVariable::fprop(), PLearn::HardSlopeVariable::fprop(), PLearn::FNetLayerVariable::fprop(), PLearn::DoubleProductVariable::fprop(), PLearn::ConfRatedAdaboostCostVariable::fprop(), PLearn::ConcatRowsVariable::fprop(), PLearn::ConcatColumnsVariable::fprop(), makeDeepCopyFromShallowCopy(), markPath(), parents(), random_sources(), PLearn::WeightedLogGaussian::recomputeSize(), PLearn::VarArrayElementVariable::recomputeSize(), PLearn::TransposedDoubleProductVariable::recomputeSize(), PLearn::SoftSlopeVariable::recomputeSize(), PLearn::SoftSlopeIntegralVariable::recomputeSize(), PLearn::PlusManyVariable::recomputeSize(), PLearn::NllSemisphericalGaussianVariable::recomputeSize(), PLearn::NllGeneralGaussianVariable::recomputeSize(), PLearn::LocalizedFeaturesLayerVariable::recomputeSize(), PLearn::LinearCombinationOfScalarVariables::recomputeSize(), PLearn::IfThenElseVariable::recomputeSize(), PLearn::HeterogenuousAffineTransformVariable::recomputeSize(), PLearn::HardSlopeVariable::recomputeSize(), PLearn::FNetLayerVariable::recomputeSize(), PLearn::DoubleProductVariable::recomputeSize(), PLearn::DiagonalizedFactorsProductVariable::recomputeSize(), PLearn::ConfRatedAdaboostCostVariable::recomputeSize(), PLearn::ConcatRowsVariable::recomputeSize(), PLearn::ConcatColumnsVariable::recomputeSize(), resizeRValue(), PLearn::ConcatRowsVariable::rfprop(), setParents(), sources(), PLearn::VarArrayElementVariable::symbolicBprop(), PLearn::ConcatRowsVariable::symbolicBprop(), PLearn::ConcatColumnsVariable::symbolicBprop(), and unmarkAncestors().


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines