|
PLearn 0.1
|
Virtual class for the parameters between two layers of an RBM. More...
#include <RBMParameters.h>


Public Member Functions | |
| RBMParameters (real the_learning_rate=0.) | |
| Default constructor. | |
| RBMParameters (string down_types, string up_types, real the_learning_rate=0.) | |
| Constructor from two string prototypes. | |
| virtual void | setAsUpInput (const Vec &input) const |
| Sets input_vec to input, and going_up to false. | |
| virtual void | setAsDownInput (const Vec &input) const |
| Sets input_vec to input, and going_up to true. | |
| virtual void | accumulatePosStats (const Vec &down_values, const Vec &up_values)=0 |
| Accumulates positive phase statistics to *_pos_stats. | |
| virtual void | accumulateNegStats (const Vec &down_values, const Vec &up_values)=0 |
| Accumulates negative phase statistics to *_neg_stats. | |
| virtual void | update ()=0 |
| Updates parameters according to contrastive divergence gradient. | |
| virtual void | update (const Vec &pos_down_values, const Vec &pos_up_values, const Vec &neg_down_values, const Vec &neg_up_values) |
| Updates parameters according to contrastive divergence gradient, not using the statistics but the explicit values passed. | |
| virtual void | clearStats ()=0 |
| Clear all information accumulated during stats. | |
| virtual void | computeUnitActivations (int start, int length, const Vec &activations) const =0 |
| Computes the vectors of activation of "length" units, starting from "start", and concatenates them into "activations". | |
| virtual void | fprop (const Vec &input, Vec &output) const |
| given the input, compute the output (possibly resize it appropriately) | |
| virtual int | nParameters (bool share_up_params, bool share_down_params) const =0 |
| return the number of parameters | |
| virtual Vec | makeParametersPointHere (const Vec &global_parameters, bool share_up_params, bool share_down_params)=0 |
| Make the parameters data be sub-vectors of the given global_parameters. | |
| virtual RBMParameters * | deepCopy (CopiesMap &copies) const |
| virtual void | build () |
| Post-constructor. | |
| virtual void | makeDeepCopyFromShallowCopy (CopiesMap &copies) |
| Transforms a shallow copy into a deep copy. | |
Static Public Member Functions | |
| static string | _classname_ () |
| static OptionList & | _getOptionList_ () |
| static RemoteMethodMap & | _getRemoteMethodMap_ () |
| static bool | _isa_ (const Object *o) |
| static void | _static_initialize_ () |
| static const PPath & | declaringFile () |
Public Attributes | |
| string | up_units_types |
| Each character of this string describes the type of an up unit: | |
| string | down_units_types |
| Same meaning as "up_units_types", but with down units. | |
| real | learning_rate |
| The learning rate, used both in update() and bpropUpdate() methods. | |
| string | initialization_method |
| The method used to initialize the weights: | |
| int | up_layer_size |
| Number of units on up layer. | |
| int | down_layer_size |
| Number of units on down layer. | |
Static Public Attributes | |
| static StaticInitializer | _static_initializer_ |
Static Protected Member Functions | |
| static void | declareOptions (OptionList &ol) |
| Declares the class options. | |
Protected Attributes | |
| Vec | input_vec |
| Points to current input vector. | |
| bool | going_up |
| Tells if input_vec comes from down (true) or up (false) | |
| int | pos_count |
| Number of examples accumulated in *_pos_stats. | |
| int | neg_count |
| Number of examples accumulated in *_neg_stats. | |
Private Types | |
| typedef OnlineLearningModule | inherited |
Private Member Functions | |
| void | build_ () |
| This does the actual building. | |
Virtual class for the parameters between two layers of an RBM.
Definition at line 58 of file RBMParameters.h.
typedef OnlineLearningModule PLearn::RBMParameters::inherited [private] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 60 of file RBMParameters.h.
| PLearn::RBMParameters::RBMParameters | ( | real | the_learning_rate = 0. | ) |
Default constructor.
Definition at line 54 of file RBMParameters.cc.
:
learning_rate(the_learning_rate),
going_up(true),
pos_count(0),
neg_count(0)
{
}
| PLearn::RBMParameters::RBMParameters | ( | string | down_types, |
| string | up_types, | ||
| real | the_learning_rate = 0. |
||
| ) |
Constructor from two string prototypes.
Definition at line 62 of file RBMParameters.cc.
References build().
:
up_units_types(up_types),
down_units_types(down_types),
learning_rate(the_learning_rate),
going_up(true),
pos_count(0),
neg_count(0)
{
// We're not sure inherited::build() has been called
build();
}

| string PLearn::RBMParameters::_classname_ | ( | ) | [static] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 52 of file RBMParameters.cc.
| OptionList & PLearn::RBMParameters::_getOptionList_ | ( | ) | [static] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 52 of file RBMParameters.cc.
| RemoteMethodMap & PLearn::RBMParameters::_getRemoteMethodMap_ | ( | ) | [static] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 52 of file RBMParameters.cc.
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 52 of file RBMParameters.cc.
| StaticInitializer RBMParameters::_static_initializer_ & PLearn::RBMParameters::_static_initialize_ | ( | ) | [static] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 52 of file RBMParameters.cc.
| virtual void PLearn::RBMParameters::accumulateNegStats | ( | const Vec & | down_values, |
| const Vec & | up_values | ||
| ) | [pure virtual] |
Accumulates negative phase statistics to *_neg_stats.
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Referenced by update().

| virtual void PLearn::RBMParameters::accumulatePosStats | ( | const Vec & | down_values, |
| const Vec & | up_values | ||
| ) | [pure virtual] |
Accumulates positive phase statistics to *_pos_stats.
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Referenced by update().

| void PLearn::RBMParameters::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::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 138 of file RBMParameters.cc.
References PLearn::OnlineLearningModule::build(), and build_().
Referenced by PLearn::RBMQLParameters::build(), PLearn::RBMLQParameters::build(), PLearn::RBMLLParameters::build(), PLearn::RBMGenericParameters::build(), PLearn::RBMConv2DLLParameters::build(), and RBMParameters().
{
inherited::build();
build_();
}


| void PLearn::RBMParameters::build_ | ( | ) | [private] |
This does the actual building.
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 116 of file RBMParameters.cc.
References down_layer_size, down_units_types, initialization_method, PLearn::OnlineLearningModule::input_size, PLearn::lowerstring(), PLearn::OnlineLearningModule::output_size, PLERROR, up_layer_size, and up_units_types.
Referenced by build().
{
up_layer_size = int(up_units_types.size());
down_layer_size = int(down_units_types.size());
if( up_layer_size == 0 || down_layer_size == 0 )
return;
string im = lowerstring( initialization_method );
if( im == "" || im == "uniform_sqrt" )
initialization_method = "uniform_sqrt";
else if( im == "uniform_linear" )
initialization_method = im;
else if( im == "zero" )
initialization_method = im;
else
PLERROR( "RBMParameters::build_ - initialization_method\n"
"\"%s\" unknown.\n", initialization_method.c_str() );
input_size = down_layer_size;
output_size = up_layer_size;
}


| virtual void PLearn::RBMParameters::clearStats | ( | ) | [pure virtual] |
Clear all information accumulated during stats.
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
| virtual void PLearn::RBMParameters::computeUnitActivations | ( | int | start, |
| int | length, | ||
| const Vec & | activations | ||
| ) | const [pure virtual] |
Computes the vectors of activation of "length" units, starting from "start", and concatenates them into "activations".
"start" indexes an up unit if "going_up", else a down unit.
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Referenced by fprop().

| void PLearn::RBMParameters::declareOptions | ( | OptionList & | ol | ) | [static, protected] |
Declares the class options.
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 75 of file RBMParameters.cc.
References PLearn::OptionBase::buildoption, PLearn::declareOption(), PLearn::OnlineLearningModule::declareOptions(), down_units_types, initialization_method, learning_rate, and up_units_types.
Referenced by PLearn::RBMQLParameters::declareOptions(), PLearn::RBMLQParameters::declareOptions(), PLearn::RBMLLParameters::declareOptions(), PLearn::RBMGenericParameters::declareOptions(), and PLearn::RBMConv2DLLParameters::declareOptions().
{
// ### Declare all of this object's options here.
// ### For the "flags" of each option, you should typically specify
// ### one of OptionBase::buildoption, OptionBase::learntoption or
// ### OptionBase::tuningoption. If you don't provide one of these three,
// ### this option will be ignored when loading values from a script.
// ### You can also combine flags, for example with OptionBase::nosave:
// ### (OptionBase::buildoption | OptionBase::nosave)
declareOption(ol, "up_units_types", &RBMParameters::up_units_types,
OptionBase::buildoption,
"Each character of this string describes the type of an"
" up unit:\n"
" - 'l' if the energy function of this unit is linear\n"
" (binomial or multinomial unit),\n"
" - 'q' if it is quadratic (for a gaussian unit).\n");
declareOption(ol, "down_units_types", &RBMParameters::down_units_types,
OptionBase::buildoption,
"Same meaning as 'up_units_types', but with down units");
declareOption(ol, "learning_rate", &RBMParameters::learning_rate,
OptionBase::buildoption,
"The learning rate, used both in update() and bpropUpdate() "
"methods\n");
declareOption(ol, "initialization_method",
&RBMParameters::initialization_method,
OptionBase::buildoption,
"The method used to initialize the weights:\n"
" - \"uniform_linear\" = a uniform law in [-1/d, 1/d]\n"
" - \"uniform_sqrt\" = a uniform law in [-1/sqrt(d),"
" 1/sqrt(d)]\n"
" - \"zero\" = all weights are set to 0,\n"
"where d = max( up_layer_size, down_layer_size ).\n");
// Now call the parent class' declareOptions
inherited::declareOptions(ol);
}


| static const PPath& PLearn::RBMParameters::declaringFile | ( | ) | [inline, static] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 155 of file RBMParameters.h.
:
//##### Not Options #####################################################
| RBMParameters * PLearn::RBMParameters::deepCopy | ( | CopiesMap & | copies | ) | const [virtual] |
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 52 of file RBMParameters.cc.
given the input, compute the output (possibly resize it appropriately)
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMJointGenericParameters, and PLearn::RBMJointLLParameters.
Definition at line 182 of file RBMParameters.cc.
References computeUnitActivations(), PLearn::OnlineLearningModule::output_size, PLearn::TVec< T >::resize(), and setAsDownInput().
{
// propagates the activations.
setAsDownInput( input );
output.resize( output_size );
computeUnitActivations( 0, output_size, output );
}

| void PLearn::RBMParameters::makeDeepCopyFromShallowCopy | ( | CopiesMap & | copies | ) | [virtual] |
Transforms a shallow copy into a deep copy.
Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 145 of file RBMParameters.cc.
References PLearn::deepCopyField(), input_vec, and PLearn::OnlineLearningModule::makeDeepCopyFromShallowCopy().
Referenced by PLearn::RBMQLParameters::makeDeepCopyFromShallowCopy(), PLearn::RBMLQParameters::makeDeepCopyFromShallowCopy(), PLearn::RBMLLParameters::makeDeepCopyFromShallowCopy(), PLearn::RBMGenericParameters::makeDeepCopyFromShallowCopy(), and PLearn::RBMConv2DLLParameters::makeDeepCopyFromShallowCopy().
{
inherited::makeDeepCopyFromShallowCopy(copies);
// ### Call deepCopyField on all "pointer-like" fields
// ### that you wish to be deepCopied rather than
// ### shallow-copied.
deepCopyField(input_vec, copies);
}


| virtual Vec PLearn::RBMParameters::makeParametersPointHere | ( | const Vec & | global_parameters, |
| bool | share_up_params, | ||
| bool | share_down_params | ||
| ) | [pure virtual] |
Make the parameters data be sub-vectors of the given global_parameters.
The argument should have size >= nParameters. The result is a Vec that starts just after this object's parameters end, i.e. result = global_parameters.subVec(nParameters(),global_parameters.size()-nParameters()); This allows to easily chain calls of this method on multiple RBMParameters.
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
| virtual int PLearn::RBMParameters::nParameters | ( | bool | share_up_params, |
| bool | share_down_params | ||
| ) | const [pure virtual] |
return the number of parameters
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
| void PLearn::RBMParameters::setAsDownInput | ( | const Vec & | input | ) | const [virtual] |
Sets input_vec to input, and going_up to true.
Reimplemented in PLearn::RBMJointGenericParameters, and PLearn::RBMJointLLParameters.
Definition at line 163 of file RBMParameters.cc.
References down_layer_size, going_up, input_vec, PLASSERT, and PLearn::TVec< T >::size().
Referenced by fprop(), PLearn::GaussianDBNClassification::greedyStep(), PLearn::GaussianDBNRegression::greedyStep(), PLearn::GaussianDBNClassification::jointGreedyStep(), PLearn::RBMJointGenericParameters::setAsDownInput(), PLearn::RBMJointLLParameters::setAsDownInput(), and PLearn::UnfrozenDeepBeliefNet::train().
{
PLASSERT( input.size() == down_layer_size );
input_vec = input;
going_up = true;
}


| void PLearn::RBMParameters::setAsUpInput | ( | const Vec & | input | ) | const [virtual] |
Sets input_vec to input, and going_up to false.
Reimplemented in PLearn::RBMJointGenericParameters, and PLearn::RBMJointLLParameters.
Definition at line 156 of file RBMParameters.cc.
References going_up, input_vec, PLASSERT, PLearn::TVec< T >::size(), and up_layer_size.
Referenced by PLearn::GaussianDBNClassification::greedyStep(), PLearn::GaussianDBNRegression::greedyStep(), PLearn::GaussianDBNClassification::jointGreedyStep(), PLearn::RBMJointGenericParameters::setAsUpInput(), PLearn::RBMJointLLParameters::setAsUpInput(), and PLearn::UnfrozenDeepBeliefNet::train().
{
PLASSERT( input.size() == up_layer_size );
input_vec = input;
going_up = false;
}


| virtual void PLearn::RBMParameters::update | ( | ) | [pure virtual] |
Updates parameters according to contrastive divergence gradient.
Implemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Referenced by update().

| void PLearn::RBMParameters::update | ( | const Vec & | pos_down_values, |
| const Vec & | pos_up_values, | ||
| const Vec & | neg_down_values, | ||
| const Vec & | neg_up_values | ||
| ) | [virtual] |
Updates parameters according to contrastive divergence gradient, not using the statistics but the explicit values passed.
Reimplemented in PLearn::RBMConv2DLLParameters, and PLearn::RBMLLParameters.
Definition at line 170 of file RBMParameters.cc.
References accumulateNegStats(), accumulatePosStats(), and update().
{
// Not-so-efficient implementation
accumulatePosStats( pos_down_values, pos_up_values );
accumulateNegStats( neg_down_values, neg_up_values );
update();
}

Reimplemented from PLearn::OnlineLearningModule.
Reimplemented in PLearn::RBMConv2DLLParameters, PLearn::RBMGenericParameters, PLearn::RBMJointGenericParameters, PLearn::RBMJointLLParameters, PLearn::RBMLLParameters, PLearn::RBMLQParameters, and PLearn::RBMQLParameters.
Definition at line 155 of file RBMParameters.h.
Number of units on down layer.
Definition at line 90 of file RBMParameters.h.
Referenced by PLearn::RBMQLParameters::accumulateNegStats(), PLearn::RBMGenericParameters::accumulateNegStats(), PLearn::RBMQLParameters::accumulatePosStats(), PLearn::RBMGenericParameters::accumulatePosStats(), PLearn::RBMLLParameters::bpropUpdate(), PLearn::RBMConv2DLLParameters::bpropUpdate(), PLearn::RBMQLParameters::bpropUpdate(), PLearn::RBMLQParameters::bpropUpdate(), PLearn::RBMLQParameters::build_(), build_(), PLearn::RBMGenericParameters::build_(), PLearn::RBMLLParameters::build_(), PLearn::RBMQLParameters::build_(), PLearn::RBMConv2DLLParameters::build_(), PLearn::RBMGenericParameters::clearStats(), PLearn::RBMQLParameters::forget(), PLearn::RBMLLParameters::forget(), PLearn::RBMLQParameters::forget(), PLearn::RBMGenericParameters::forget(), PLearn::RBMConv2DLLParameters::forget(), setAsDownInput(), PLearn::RBMGenericParameters::update(), PLearn::RBMConv2DLLParameters::update(), PLearn::RBMQLParameters::update(), and PLearn::RBMLQParameters::update().
Same meaning as "up_units_types", but with down units.
Definition at line 72 of file RBMParameters.h.
Referenced by PLearn::RBMGenericParameters::accumulateNegStats(), PLearn::RBMGenericParameters::accumulatePosStats(), PLearn::RBMLQParameters::build_(), build_(), PLearn::RBMGenericParameters::build_(), PLearn::RBMLLParameters::build_(), PLearn::RBMQLParameters::build_(), PLearn::RBMConv2DLLParameters::build_(), PLearn::RBMJointGenericParameters::build_units_types(), PLearn::RBMJointLLParameters::build_units_types(), and declareOptions().
bool PLearn::RBMParameters::going_up [mutable, protected] |
Tells if input_vec comes from down (true) or up (false)
Definition at line 170 of file RBMParameters.h.
Referenced by PLearn::RBMJointLLParameters::setAsCondInput(), PLearn::RBMJointGenericParameters::setAsCondInput(), setAsDownInput(), and setAsUpInput().
The method used to initialize the weights:
Definition at line 82 of file RBMParameters.h.
Referenced by build_(), declareOptions(), PLearn::RBMQLParameters::forget(), PLearn::RBMLLParameters::forget(), PLearn::RBMLQParameters::forget(), PLearn::RBMGenericParameters::forget(), and PLearn::RBMConv2DLLParameters::forget().
Vec PLearn::RBMParameters::input_vec [mutable, protected] |
Points to current input vector.
Definition at line 167 of file RBMParameters.h.
Referenced by makeDeepCopyFromShallowCopy(), PLearn::RBMJointLLParameters::setAsCondInput(), PLearn::RBMJointGenericParameters::setAsCondInput(), setAsDownInput(), and setAsUpInput().
The learning rate, used both in update() and bpropUpdate() methods.
Definition at line 75 of file RBMParameters.h.
Referenced by PLearn::RBMConv2DLLParameters::bpropUpdate(), PLearn::RBMLLParameters::bpropUpdate(), PLearn::RBMQLParameters::bpropUpdate(), PLearn::RBMJointLLParameters::bpropUpdate(), PLearn::RBMLQParameters::bpropUpdate(), declareOptions(), PLearn::GaussPartSupervisedDBN::jointGreedyStep(), PLearn::PartSupervisedDBN::jointGreedyStep(), PLearn::RBMGenericParameters::update(), PLearn::RBMConv2DLLParameters::update(), PLearn::RBMQLParameters::update(), PLearn::RBMLLParameters::update(), and PLearn::RBMLQParameters::update().
int PLearn::RBMParameters::neg_count [protected] |
Number of examples accumulated in *_neg_stats.
Definition at line 175 of file RBMParameters.h.
Referenced by PLearn::RBMLLParameters::accumulateNegStats(), PLearn::RBMQLParameters::accumulateNegStats(), PLearn::RBMLQParameters::accumulateNegStats(), PLearn::RBMGenericParameters::accumulateNegStats(), PLearn::RBMConv2DLLParameters::accumulateNegStats(), PLearn::RBMQLParameters::clearStats(), PLearn::RBMConv2DLLParameters::clearStats(), PLearn::RBMLLParameters::clearStats(), PLearn::RBMGenericParameters::clearStats(), PLearn::RBMLQParameters::clearStats(), PLearn::RBMGenericParameters::update(), PLearn::RBMConv2DLLParameters::update(), PLearn::RBMQLParameters::update(), PLearn::RBMLLParameters::update(), and PLearn::RBMLQParameters::update().
int PLearn::RBMParameters::pos_count [protected] |
Number of examples accumulated in *_pos_stats.
Definition at line 173 of file RBMParameters.h.
Referenced by PLearn::RBMLQParameters::accumulatePosStats(), PLearn::RBMLLParameters::accumulatePosStats(), PLearn::RBMQLParameters::accumulatePosStats(), PLearn::RBMGenericParameters::accumulatePosStats(), PLearn::RBMConv2DLLParameters::accumulatePosStats(), PLearn::RBMQLParameters::clearStats(), PLearn::RBMConv2DLLParameters::clearStats(), PLearn::RBMLLParameters::clearStats(), PLearn::RBMGenericParameters::clearStats(), PLearn::RBMLQParameters::clearStats(), PLearn::RBMGenericParameters::update(), PLearn::RBMConv2DLLParameters::update(), PLearn::RBMQLParameters::update(), PLearn::RBMLLParameters::update(), and PLearn::RBMLQParameters::update().
Number of units on up layer.
Definition at line 87 of file RBMParameters.h.
Referenced by PLearn::RBMLQParameters::accumulateNegStats(), PLearn::RBMGenericParameters::accumulateNegStats(), PLearn::RBMLQParameters::accumulatePosStats(), PLearn::RBMGenericParameters::accumulatePosStats(), PLearn::RBMLLParameters::bpropUpdate(), PLearn::RBMConv2DLLParameters::bpropUpdate(), PLearn::RBMQLParameters::bpropUpdate(), PLearn::RBMJointLLParameters::bpropUpdate(), PLearn::RBMLQParameters::bpropUpdate(), PLearn::RBMLQParameters::build_(), build_(), PLearn::RBMGenericParameters::build_(), PLearn::RBMLLParameters::build_(), PLearn::RBMQLParameters::build_(), PLearn::RBMConv2DLLParameters::build_(), PLearn::RBMGenericParameters::clearStats(), PLearn::RBMQLParameters::forget(), PLearn::RBMLLParameters::forget(), PLearn::RBMLQParameters::forget(), PLearn::RBMGenericParameters::forget(), PLearn::RBMConv2DLLParameters::forget(), setAsUpInput(), PLearn::RBMGenericParameters::update(), PLearn::RBMConv2DLLParameters::update(), PLearn::RBMQLParameters::update(), and PLearn::RBMLQParameters::update().
Each character of this string describes the type of an up unit:
Definition at line 69 of file RBMParameters.h.
Referenced by PLearn::RBMGenericParameters::accumulateNegStats(), PLearn::RBMGenericParameters::accumulatePosStats(), PLearn::RBMLQParameters::build_(), build_(), PLearn::RBMGenericParameters::build_(), PLearn::RBMLLParameters::build_(), PLearn::RBMQLParameters::build_(), PLearn::RBMConv2DLLParameters::build_(), PLearn::RBMJointGenericParameters::build_units_types(), PLearn::RBMJointLLParameters::build_units_types(), and declareOptions().
1.7.4