PLearn 0.1
|
Layer in an RBM formed with binomial units. More...
#include <RBMMultinomialLayer.h>
Public Member Functions | |
RBMMultinomialLayer () | |
Default constructor. | |
RBMMultinomialLayer (int the_size) | |
Constructor from the number of units in the multinomial. | |
virtual void | getUnitActivations (int i, PP< RBMParameters > rbmp, int offset=0) |
Uses "rbmp" to obtain the activations of unit "i" of this layer. | |
virtual void | getAllActivations (PP< RBMParameters > rbmp, int offset=0) |
Uses "rbmp" to obtain the activations of all units in this layer. | |
virtual void | generateSample () |
generate a sample, and update the sample field | |
virtual void | computeExpectation () |
compute the expectation | |
virtual void | bpropUpdate (const Vec &input, const Vec &output, Vec &input_gradient, const Vec &output_gradient) |
back-propagates the output gradient to the input | |
virtual string | classname () const |
virtual OptionList & | getOptionList () const |
virtual OptionMap & | getOptionMap () const |
virtual RemoteMethodMap & | getRemoteMethodMap () const |
virtual RBMMultinomialLayer * | deepCopy (CopiesMap &copies) const |
virtual void | build () |
Post-constructor. | |
virtual void | makeDeepCopyFromShallowCopy (CopiesMap &copies) |
Transforms a shallow copy into a deep copy. | |
RBMMultinomialLayer (real the_learning_rate=0.) | |
Default constructor. | |
RBMMultinomialLayer (int the_size, real the_learning_rate=0.) | |
Constructor from the number of units in the multinomial. | |
virtual void | generateSample () |
generate a sample, and update the sample field | |
virtual void | generateSamples () |
batch version | |
virtual void | computeExpectation () |
compute the expectation | |
virtual void | computeExpectations () |
batch version | |
virtual void | fprop (const Vec &input, Vec &output) const |
forward propagation | |
virtual void | fprop (const Vec &input, const Vec &rbm_bias, Vec &output) const |
forward propagation with provided bias | |
virtual void | bpropUpdate (const Vec &input, const Vec &output, Vec &input_gradient, const Vec &output_gradient, bool accumulate=false) |
back-propagates the output gradient to the input | |
virtual void | bpropUpdate (const Mat &inputs, const Mat &outputs, Mat &input_gradients, const Mat &output_gradients, bool accumulate=false) |
Back-propagate the output gradient to the input, and update parameters. | |
virtual void | bpropUpdate (const Vec &input, const Vec &rbm_bias, const Vec &output, Vec &input_gradient, Vec &rbm_bias_gradient, const Vec &output_gradient) |
back-propagates the output gradient to the input and the bias | |
virtual real | fpropNLL (const Vec &target) |
Computes the negative log-likelihood of target given the internal activations of the layer. | |
virtual void | fpropNLL (const Mat &targets, const Mat &costs_column) |
virtual void | bpropNLL (const Vec &target, real nll, Vec &bias_gradient) |
Computes the gradient of the negative log-likelihood of target with respect to the layer's bias, given the internal activations. | |
virtual void | bpropNLL (const Mat &targets, const Mat &costs_column, Mat &bias_gradients) |
virtual real | energy (const Vec &unit_values) const |
virtual real | freeEnergyContribution (const Vec &unit_activations) const |
Computes ![]() | |
virtual void | freeEnergyContributionGradient (const Vec &unit_activations, Vec &unit_activations_gradient, real output_gradient=1, bool accumulate=false) const |
Computes gradient of the result of freeEnergyContribution ![]() | |
virtual int | getConfigurationCount () |
Returns a number of different configurations the layer can be in. | |
virtual void | getConfiguration (int conf_index, Vec &output) |
Computes the conf_index configuration of the layer. | |
virtual string | classname () const |
virtual OptionList & | getOptionList () const |
virtual OptionMap & | getOptionMap () const |
virtual RemoteMethodMap & | getRemoteMethodMap () const |
virtual RBMMultinomialLayer * | 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 Object * | _new_instance_for_typemap_ () |
static bool | _isa_ (const Object *o) |
static void | _static_initialize_ () |
static const PPath & | declaringFile () |
static string | _classname_ () |
static OptionList & | _getOptionList_ () |
static RemoteMethodMap & | _getRemoteMethodMap_ () |
static Object * | _new_instance_for_typemap_ () |
static bool | _isa_ (const Object *o) |
static void | _static_initialize_ () |
static const PPath & | declaringFile () |
Static Public Attributes | |
static StaticInitializer | _static_initializer_ |
Static Protected Member Functions | |
static void | declareOptions (OptionList &ol) |
Declares the class options. | |
static void | declareOptions (OptionList &ol) |
Declares the class options. | |
Protected Attributes | |
Vec | tmp_softmax |
Private Types | |
typedef RBMLayer | inherited |
typedef RBMLayer | inherited |
Private Member Functions | |
void | build_ () |
This does the actual building. | |
void | build_ () |
This does the actual building. |
Layer in an RBM formed with binomial units.
Layer in an RBM consisting in one multinomial unit.
Definition at line 54 of file DEPRECATED/RBMMultinomialLayer.h.
typedef RBMLayer PLearn::RBMMultinomialLayer::inherited [private] |
Reimplemented from PLearn::RBMLayer.
Definition at line 56 of file DEPRECATED/RBMMultinomialLayer.h.
typedef RBMLayer PLearn::RBMMultinomialLayer::inherited [private] |
Reimplemented from PLearn::RBMLayer.
Definition at line 55 of file RBMMultinomialLayer.h.
PLearn::RBMMultinomialLayer::RBMMultinomialLayer | ( | ) |
PLearn::RBMMultinomialLayer::RBMMultinomialLayer | ( | int | the_size | ) |
Constructor from the number of units in the multinomial.
Definition at line 55 of file DEPRECATED/RBMMultinomialLayer.cc.
References PLearn::TVec< T >::resize(), and PLearn::sample().
{ size = the_size; units_types = string( the_size, 'l' ); activations.resize( the_size ); sample.resize( the_size ); expectation.resize( the_size ); expectation_is_up_to_date = false; }
PLearn::RBMMultinomialLayer::RBMMultinomialLayer | ( | real | the_learning_rate = 0. | ) |
Default constructor.
Definition at line 53 of file RBMMultinomialLayer.cc.
: inherited( the_learning_rate ) { }
Constructor from the number of units in the multinomial.
Definition at line 58 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::activation, PLearn::RBMLayer::bias, PLearn::RBMLayer::bias_neg_stats, PLearn::RBMLayer::bias_pos_stats, PLearn::RBMLayer::expectation, PLearn::TVec< T >::resize(), PLearn::RBMLayer::sample, and PLearn::RBMLayer::size.
: inherited( the_learning_rate ) { size = the_size; activation.resize( the_size ); sample.resize( the_size ); expectation.resize( the_size ); bias.resize( the_size ); bias_pos_stats.resize( the_size ); bias_neg_stats.resize( the_size ); }
string PLearn::RBMMultinomialLayer::_classname_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
static string PLearn::RBMMultinomialLayer::_classname_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
OptionList & PLearn::RBMMultinomialLayer::_getOptionList_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
static OptionList& PLearn::RBMMultinomialLayer::_getOptionList_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
RemoteMethodMap & PLearn::RBMMultinomialLayer::_getRemoteMethodMap_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
static RemoteMethodMap& PLearn::RBMMultinomialLayer::_getRemoteMethodMap_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
Reimplemented from PLearn::RBMLayer.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
Reimplemented from PLearn::RBMLayer.
static Object* PLearn::RBMMultinomialLayer::_new_instance_for_typemap_ | ( | ) | [static] |
Reimplemented from PLearn::Object.
Object * PLearn::RBMMultinomialLayer::_new_instance_for_typemap_ | ( | ) | [static] |
Reimplemented from PLearn::Object.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
StaticInitializer RBMMultinomialLayer::_static_initializer_ & PLearn::RBMMultinomialLayer::_static_initialize_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
static void PLearn::RBMMultinomialLayer::_static_initialize_ | ( | ) | [static] |
Reimplemented from PLearn::RBMLayer.
void PLearn::RBMMultinomialLayer::bpropNLL | ( | const Vec & | target, |
real | nll, | ||
Vec & | bias_gradient | ||
) | [virtual] |
Computes the gradient of the negative log-likelihood of target with respect to the layer's bias, given the internal activations.
Reimplemented from PLearn::RBMLayer.
Definition at line 377 of file RBMMultinomialLayer.cc.
References computeExpectation(), PLearn::RBMLayer::expectation, PLearn::OnlineLearningModule::input_size, PLASSERT, PLearn::TVec< T >::resize(), PLearn::TVec< T >::size(), PLearn::RBMLayer::size, and PLearn::substract().
{ computeExpectation(); PLASSERT( target.size() == input_size ); bias_gradient.resize( size ); // bias_gradient = expectation - target substract(expectation, target, bias_gradient); }
void PLearn::RBMMultinomialLayer::bpropNLL | ( | const Mat & | targets, |
const Mat & | costs_column, | ||
Mat & | bias_gradients | ||
) | [virtual] |
Reimplemented from PLearn::RBMLayer.
Definition at line 389 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::batch_size, computeExpectations(), PLearn::RBMLayer::expectations, PLearn::OnlineLearningModule::input_size, PLearn::TMat< T >::length(), PLASSERT, PLearn::TMat< T >::resize(), PLearn::RBMLayer::size, PLearn::substract(), and PLearn::TMat< T >::width().
{ computeExpectations(); PLASSERT( targets.width() == input_size ); PLASSERT( targets.length() == batch_size ); PLASSERT( costs_column.width() == 1 ); PLASSERT( costs_column.length() == batch_size ); bias_gradients.resize( batch_size, size ); // bias_gradients = expectations - targets substract(expectations, targets, bias_gradients); }
void PLearn::RBMMultinomialLayer::bpropUpdate | ( | const Vec & | input, |
const Vec & | output, | ||
Vec & | input_gradient, | ||
const Vec & | output_gradient | ||
) | [virtual] |
back-propagates the output gradient to the input
Implements PLearn::RBMLayer.
Definition at line 100 of file DEPRECATED/RBMMultinomialLayer.cc.
References PLERROR.
{ PLERROR( "RBMMultinomialLayer::bpropUpdate not implemented yet." ); }
void PLearn::RBMMultinomialLayer::bpropUpdate | ( | const Vec & | input, |
const Vec & | output, | ||
Vec & | input_gradient, | ||
const Vec & | output_gradient, | ||
bool | accumulate = false |
||
) | [virtual] |
back-propagates the output gradient to the input
Implements PLearn::RBMLayer.
Definition at line 152 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::applyBiasDecay(), b, PLearn::RBMLayer::bias, PLearn::RBMLayer::bias_inc, PLearn::TVec< T >::clear(), PLearn::TVec< T >::data(), PLearn::dot(), i, PLearn::RBMLayer::learning_rate, PLearn::RBMLayer::momentum, PLASSERT, PLASSERT_MSG, PLearn::TVec< T >::resize(), PLearn::RBMLayer::size, and PLearn::TVec< T >::size().
{ PLASSERT( input.size() == size ); PLASSERT( output.size() == size ); PLASSERT( output_gradient.size() == size ); if( accumulate ) { PLASSERT_MSG( input_gradient.size() == size, "Cannot resize input_gradient AND accumulate into it" ); } else { input_gradient.resize( size ); input_gradient.clear(); } if( momentum != 0. ) bias_inc.resize( size ); // input_gradient[i] = // (output_gradient[i] - output_gradient . output) output[i] real outg_dot_out = dot( output_gradient, output ); real* out = output.data(); real* outg = output_gradient.data(); real* ing = input_gradient.data(); real* b = bias.data(); real* binc = momentum==0?0:bias_inc.data(); for( int i=0 ; i<size ; i++ ) { real ing_i = (outg[i] - outg_dot_out) * out[i]; ing[i] += ing_i; if( momentum == 0. ) { // update the bias: bias -= learning_rate * input_gradient b[i] -= learning_rate * ing_i; } else { // The update rule becomes: // bias_inc = momentum * bias_inc - learning_rate * input_gradient // bias += bias_inc binc[i] = momentum * binc[i] - learning_rate * ing_i; b[i] += binc[i]; } } applyBiasDecay(); }
void PLearn::RBMMultinomialLayer::bpropUpdate | ( | const Mat & | inputs, |
const Mat & | outputs, | ||
Mat & | input_gradients, | ||
const Mat & | output_gradients, | ||
bool | accumulate = false |
||
) | [virtual] |
Back-propagate the output gradient to the input, and update parameters.
Implements PLearn::RBMLayer.
Definition at line 206 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::applyBiasDecay(), b, PLearn::RBMLayer::bias, PLearn::RBMLayer::bias_inc, PLearn::TMat< T >::clear(), PLearn::TMat< T >::data(), PLearn::TVec< T >::data(), PLearn::dot(), i, PLearn::RBMLayer::learning_rate, PLearn::TMat< T >::length(), PLearn::RBMLayer::momentum, PLASSERT, PLASSERT_MSG, PLCHECK_MSG, PLearn::TMat< T >::resize(), PLearn::TVec< T >::resize(), PLearn::RBMLayer::size, and PLearn::TMat< T >::width().
{ PLASSERT( inputs.width() == size ); PLASSERT( outputs.width() == size ); PLASSERT( output_gradients.width() == size ); int mbatch_size = inputs.length(); PLASSERT( outputs.length() == mbatch_size ); PLASSERT( output_gradients.length() == mbatch_size ); if( accumulate ) { PLASSERT_MSG( input_gradients.width() == size && input_gradients.length() == inputs.length(), "Cannot resize input_gradient and accumulate into it." ); } else { input_gradients.resize(inputs.length(), size); input_gradients.clear(); } if( momentum != 0. ) bias_inc.resize( size ); // TODO see if we can have a speed-up by reorganizing the different steps // input_gradients[k][i] = // (output_gradients[k][i]-output_gradients[k].outputs[k]) outputs[k][i] real mean_lr = learning_rate / mbatch_size; for( int k=0; k<mbatch_size; k++ ) { real outg_dot_out = dot( output_gradients(k), outputs(k) ); real* out = outputs(k).data(); real* outg = output_gradients(k).data(); real* ing = input_gradients(k).data(); real* b = bias.data(); real* binc = momentum==0?0:bias_inc.data(); for( int i=0 ; i<size ; i++ ) { real ing_ki = (outg[i] - outg_dot_out) * out[i]; ing[i] += ing_ki; if( momentum == 0. ) { // update the bias: bias -= learning_rate * input_gradient b[i] -= mean_lr * ing_ki; } else { PLCHECK_MSG(false, "Momentum not correctly implemented with batch"); // The update rule becomes: // bias_inc = momentum*bias_inc - learning_rate*input_gradient // bias += bias_inc binc[i] = momentum * binc[i] - mean_lr * ing_ki; b[i] += binc[i]; } } } applyBiasDecay(); }
void PLearn::RBMMultinomialLayer::bpropUpdate | ( | const Vec & | input, |
const Vec & | rbm_bias, | ||
const Vec & | output, | ||
Vec & | input_gradient, | ||
Vec & | rbm_bias_gradient, | ||
const Vec & | output_gradient | ||
) | [virtual] |
back-propagates the output gradient to the input and the bias
TODO: add "accumulate" here.
Reimplemented from PLearn::RBMLayer.
Definition at line 275 of file RBMMultinomialLayer.cc.
References PLearn::TVec< T >::data(), PLearn::dot(), i, PLASSERT, PLearn::TVec< T >::resize(), PLearn::TVec< T >::size(), and PLearn::RBMLayer::size.
{ PLASSERT( input.size() == size ); PLASSERT( rbm_bias.size() == size ); PLASSERT( output.size() == size ); PLASSERT( output_gradient.size() == size ); input_gradient.resize( size ); rbm_bias_gradient.resize( size ); // input_gradient[i] = // (output_gradient . output - output_gradient[i] ) output[i] real outg_dot_out = dot( output_gradient, output ); real* out = output.data(); real* outg = output_gradient.data(); real* ing = input_gradient.data(); for( int i=0 ; i<size ; i++ ) ing[i] = (outg[i] - outg_dot_out) * out[i]; rbm_bias_gradient << input_gradient; }
void PLearn::RBMMultinomialLayer::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::RBMLayer.
Definition at line 132 of file DEPRECATED/RBMMultinomialLayer.cc.
{ inherited::build(); build_(); }
virtual void PLearn::RBMMultinomialLayer::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::RBMLayer.
void PLearn::RBMMultinomialLayer::build_ | ( | ) | [private] |
This does the actual building.
Reimplemented from PLearn::RBMLayer.
Definition at line 119 of file DEPRECATED/RBMMultinomialLayer.cc.
References PLearn::TVec< T >::resize(), and PLearn::sample().
{ if( size < 0 ) size = int(units_types.size()); if( size != (int) units_types.size() ) units_types = string( size, 'l' ); activations.resize( size ); sample.resize( size ); expectation.resize( size ); expectation_is_up_to_date = false; }
void PLearn::RBMMultinomialLayer::build_ | ( | ) | [private] |
This does the actual building.
Reimplemented from PLearn::RBMLayer.
virtual string PLearn::RBMMultinomialLayer::classname | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
string PLearn::RBMMultinomialLayer::classname | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
void PLearn::RBMMultinomialLayer::computeExpectation | ( | ) | [virtual] |
compute the expectation
Implements PLearn::RBMLayer.
Definition at line 90 of file DEPRECATED/RBMMultinomialLayer.cc.
References PLearn::softmaxMinus().
Referenced by bpropNLL(), and fpropNLL().
{ if( expectation_is_up_to_date ) return; // expectation = softmax(-activations) softmaxMinus(activations, expectation); expectation_is_up_to_date = true; }
virtual void PLearn::RBMMultinomialLayer::computeExpectation | ( | ) | [virtual] |
compute the expectation
Implements PLearn::RBMLayer.
void PLearn::RBMMultinomialLayer::computeExpectations | ( | ) | [virtual] |
batch version
Implements PLearn::RBMLayer.
Definition at line 110 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::activations, PLearn::RBMLayer::batch_size, PLearn::RBMLayer::expectations, PLearn::RBMLayer::expectations_are_up_to_date, PLearn::TMat< T >::length(), PLASSERT, PLearn::RBMLayer::size, PLearn::softmax(), and PLearn::TMat< T >::width().
Referenced by bpropNLL(), and fpropNLL().
{ if( expectations_are_up_to_date ) return; PLASSERT( expectations.width() == size && expectations.length() == batch_size ); // expectation = softmax(-activation) for (int k = 0; k < batch_size; k++) softmax(activations(k), expectations(k)); expectations_are_up_to_date = true; }
static void PLearn::RBMMultinomialLayer::declareOptions | ( | OptionList & | ol | ) | [static, protected] |
Declares the class options.
Reimplemented from PLearn::RBMLayer.
void PLearn::RBMMultinomialLayer::declareOptions | ( | OptionList & | ol | ) | [static, protected] |
Declares the class options.
Reimplemented from PLearn::RBMLayer.
Definition at line 108 of file DEPRECATED/RBMMultinomialLayer.cc.
{ /* declareOption(ol, "size", &RBMMultinomialLayer::size, OptionBase::buildoption, "Number of units."); */ // Now call the parent class' declareOptions inherited::declareOptions(ol); }
static const PPath& PLearn::RBMMultinomialLayer::declaringFile | ( | ) | [inline, static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 98 of file DEPRECATED/RBMMultinomialLayer.h.
:
//##### Not Options #####################################################
static const PPath& PLearn::RBMMultinomialLayer::declaringFile | ( | ) | [inline, static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 145 of file RBMMultinomialLayer.h.
:
//##### Not Options #####################################################
virtual RBMMultinomialLayer* PLearn::RBMMultinomialLayer::deepCopy | ( | CopiesMap & | copies | ) | const [virtual] |
Reimplemented from PLearn::RBMLayer.
RBMMultinomialLayer * PLearn::RBMMultinomialLayer::deepCopy | ( | CopiesMap & | copies | ) | const [virtual] |
Reimplemented from PLearn::RBMLayer.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
Reimplemented from PLearn::RBMLayer.
Definition at line 432 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::bias, and PLearn::dot().
forward propagation
Reimplemented from PLearn::RBMLayer.
Definition at line 126 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::bias, PLearn::OnlineLearningModule::input_size, PLearn::OnlineLearningModule::output_size, PLASSERT, PLearn::TVec< T >::resize(), PLearn::TVec< T >::size(), and PLearn::softmax().
{ PLASSERT( input.size() == input_size ); output.resize( output_size ); // inefficient softmax( input+bias, output ); }
void PLearn::RBMMultinomialLayer::fprop | ( | const Vec & | input, |
const Vec & | rbm_bias, | ||
Vec & | output | ||
) | const [virtual] |
forward propagation with provided bias
Reimplemented from PLearn::RBMLayer.
Definition at line 138 of file RBMMultinomialLayer.cc.
References PLearn::OnlineLearningModule::input_size, PLearn::OnlineLearningModule::output_size, PLASSERT, PLearn::TVec< T >::resize(), PLearn::TVec< T >::size(), and PLearn::softmax().
{ PLASSERT( input.size() == input_size ); PLASSERT( rbm_bias.size() == input_size ); output.resize( output_size ); // inefficient softmax( input+rbm_bias, output ); }
void PLearn::RBMMultinomialLayer::fpropNLL | ( | const Mat & | targets, |
const Mat & | costs_column | ||
) | [virtual] |
Reimplemented from PLearn::RBMLayer.
Definition at line 336 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::batch_size, computeExpectations(), PLearn::RBMLayer::expectation, PLearn::RBMLayer::expectations, PLearn::fast_exact_is_equal(), PLearn::TMat< T >::hasMissing(), i, PLearn::OnlineLearningModule::input_size, PLearn::is_equal(), PLearn::TMat< T >::length(), PLearn::min(), pl_log, PLASSERT, PLASSERT_MSG, PLERROR, PLearn::RBMLayer::size, PLearn::sum(), and PLearn::TMat< T >::width().
{ computeExpectations(); PLASSERT( targets.width() == input_size ); PLASSERT( targets.length() == batch_size ); PLASSERT( costs_column.width() == 1 ); PLASSERT( costs_column.length() == batch_size ); real target_i, expectation_i; for (int k=0; k<batch_size; k++) // loop over minibatch { #ifdef BOUNDCHECK if (!targets(k).hasMissing()) { PLASSERT_MSG( min(targets(k)) >= 0., "Elements of \"targets\" should be positive" ); // Ensure the distribution probabilities sum to 1. We relax a // bit the default tolerance as probabilities using // exponentials could suffer numerical imprecisions. if (!is_equal( sum(targets(k)), 1., 1., 1e-5, 1e-5 )) PLERROR("In RBMMultinomialLayer::fpropNLL - Elements of" " \"target\" should sum to 1 (found a sum = %f at row" " %d)", sum(targets(k)), k); } #endif real nll = 0; real* expectation = expectations[k]; real* target = targets[k]; for(int i=0; i<size; i++) { target_i = target[i]; expectation_i = expectation[i]; if(!fast_exact_is_equal(target_i, 0.0)) nll -= target_i * pl_log(expectation_i); } costs_column(k, 0) = nll; } }
Computes the negative log-likelihood of target given the internal activations of the layer.
Reimplemented from PLearn::RBMLayer.
Definition at line 303 of file RBMMultinomialLayer.cc.
References computeExpectation(), PLearn::RBMLayer::expectation, PLearn::fast_exact_is_equal(), PLearn::TVec< T >::hasMissing(), i, PLearn::OnlineLearningModule::input_size, PLearn::is_equal(), PLearn::min(), pl_log, PLASSERT, PLASSERT_MSG, PLERROR, PLearn::TVec< T >::size(), PLearn::RBMLayer::size, and PLearn::sum().
{ computeExpectation(); PLASSERT( target.size() == input_size ); #ifdef BOUNDCHECK if (!target.hasMissing()) { PLASSERT_MSG( min(target) >= 0., "Elements of \"target\" should be positive" ); // Ensure the distribution probabilities sum to 1. We relax a // bit the default tolerance as probabilities using // exponentials could suffer numerical imprecisions. if (!is_equal( sum(target), 1., 1., 1e-5, 1e-5 )) PLERROR("In RBMMultinomialLayer::fpropNLL - Elements of \"target\"" " should sum to 1 (found a sum = %f)", sum(target)); } #endif real nll = 0; real target_i, expectation_i; for (int i=0; i<size; i++) { target_i = target[i]; expectation_i = expectation[i]; if(!fast_exact_is_equal(target_i, 0.0)) nll -= target_i * pl_log(expectation_i); } return nll; }
real PLearn::RBMMultinomialLayer::freeEnergyContribution | ( | const Vec & | unit_activations | ) | const [virtual] |
Computes This quantity is used for computing the free energy of a sample x in the OTHER layer of an RBM, from which unit_activations was computed.
Reimplemented from PLearn::RBMLayer.
Definition at line 437 of file RBMMultinomialLayer.cc.
References PLearn::logadd().
{ // result = -log(\sum_{i=0}^{size-1} exp(a_i)) return -logadd(unit_activations); }
void PLearn::RBMMultinomialLayer::freeEnergyContributionGradient | ( | const Vec & | unit_activations, |
Vec & | unit_activations_gradient, | ||
real | output_gradient = 1 , |
||
bool | accumulate = false |
||
) | const [virtual] |
Computes gradient of the result of freeEnergyContribution with respect to unit_activations.
Optionally, a gradient with respect to freeEnergyContribution can be given
Reimplemented from PLearn::RBMLayer.
Definition at line 444 of file RBMMultinomialLayer.cc.
References PLearn::TVec< T >::clear(), PLearn::TVec< T >::data(), PLASSERT, PLearn::TVec< T >::resize(), PLearn::TVec< T >::size(), PLearn::RBMLayer::size, PLearn::softmax(), and tmp_softmax.
{ PLASSERT( unit_activations.size() == size ); unit_activations_gradient.resize( size ); if( !accumulate ) unit_activations_gradient.clear(); tmp_softmax.resize( size ); softmax(unit_activations, tmp_softmax); real* ga = unit_activations_gradient.data(); real* s = tmp_softmax.data(); for (int i=0; i<size; i++) ga[i] -= output_gradient * s[i]; }
void PLearn::RBMMultinomialLayer::generateSample | ( | ) | [virtual] |
generate a sample, and update the sample field
Implements PLearn::RBMLayer.
Definition at line 82 of file DEPRECATED/RBMMultinomialLayer.cc.
References PLearn::fill_one_hot(), i, and PLearn::sample().
{ computeExpectation(); int i = random_gen->multinomial_sample( expectation ); fill_one_hot( sample, i, 0., 1. ); }
virtual void PLearn::RBMMultinomialLayer::generateSample | ( | ) | [virtual] |
generate a sample, and update the sample field
Implements PLearn::RBMLayer.
void PLearn::RBMMultinomialLayer::generateSamples | ( | ) | [virtual] |
batch version
Implements PLearn::RBMLayer.
Definition at line 83 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::batch_size, PLearn::RBMLayer::expectations, PLearn::RBMLayer::expectations_are_up_to_date, PLearn::fill_one_hot(), PLearn::TMat< T >::length(), PLASSERT, PLASSERT_MSG, PLCHECK_MSG, PLearn::RBMLayer::random_gen, PLearn::RBMLayer::samples, PLearn::RBMLayer::size, and PLearn::TMat< T >::width().
{ PLASSERT_MSG(random_gen, "random_gen should be initialized before generating samples"); PLCHECK_MSG(expectations_are_up_to_date, "Expectations should be computed " "before calling generateSamples()"); PLASSERT( samples.width() == size && samples.length() == batch_size ); for (int k = 0; k < batch_size; k++) { int i = random_gen->multinomial_sample( expectations(k) ); fill_one_hot( samples(k), i, real(0.), real(1.) ); } }
void PLearn::RBMMultinomialLayer::getAllActivations | ( | PP< RBMParameters > | rbmp, |
int | offset = 0 |
||
) | [virtual] |
Uses "rbmp" to obtain the activations of all units in this layer.
Unit 0 of this layer corresponds to unit "offset" of "rbmp".
Implements PLearn::RBMLayer.
Definition at line 75 of file DEPRECATED/RBMMultinomialLayer.cc.
{ rbmp->computeUnitActivations( offset, size, activations ); expectation_is_up_to_date = false; }
Computes the conf_index configuration of the layer.
Reimplemented from PLearn::RBMLayer.
Definition at line 465 of file RBMMultinomialLayer.cc.
References getConfigurationCount(), i, PLearn::TVec< T >::length(), PLASSERT, and PLearn::RBMLayer::size.
{ PLASSERT( output.length() == size ); PLASSERT( conf_index >= 0 && conf_index < getConfigurationCount() ); for ( int i = 0; i < size; ++i ) { output[i] = i == conf_index ? 1 : 0; } }
int PLearn::RBMMultinomialLayer::getConfigurationCount | ( | ) | [virtual] |
Returns a number of different configurations the layer can be in.
Reimplemented from PLearn::RBMLayer.
Definition at line 460 of file RBMMultinomialLayer.cc.
References PLearn::RBMLayer::size.
Referenced by getConfiguration().
{ return size; }
virtual OptionList& PLearn::RBMMultinomialLayer::getOptionList | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
OptionList & PLearn::RBMMultinomialLayer::getOptionList | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
OptionMap & PLearn::RBMMultinomialLayer::getOptionMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
virtual OptionMap& PLearn::RBMMultinomialLayer::getOptionMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
virtual RemoteMethodMap& PLearn::RBMMultinomialLayer::getRemoteMethodMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
RemoteMethodMap & PLearn::RBMMultinomialLayer::getRemoteMethodMap | ( | ) | const [virtual] |
Reimplemented from PLearn::Object.
Definition at line 49 of file DEPRECATED/RBMMultinomialLayer.cc.
void PLearn::RBMMultinomialLayer::getUnitActivations | ( | int | i, |
PP< RBMParameters > | rbmp, | ||
int | offset = 0 |
||
) | [virtual] |
Uses "rbmp" to obtain the activations of unit "i" of this layer.
This activation vector is computed by the "i+offset"-th unit of "rbmp"
Implements PLearn::RBMLayer.
Definition at line 67 of file DEPRECATED/RBMMultinomialLayer.cc.
References PLearn::TVec< T >::subVec().
{ Vec activation = activations.subVec( i, 1 ); rbmp->computeUnitActivations( i+offset, 1, activation ); expectation_is_up_to_date = false; }
virtual void PLearn::RBMMultinomialLayer::makeDeepCopyFromShallowCopy | ( | CopiesMap & | copies | ) | [virtual] |
Transforms a shallow copy into a deep copy.
Reimplemented from PLearn::RBMLayer.
void PLearn::RBMMultinomialLayer::makeDeepCopyFromShallowCopy | ( | CopiesMap & | copies | ) | [virtual] |
Transforms a shallow copy into a deep copy.
Reimplemented from PLearn::RBMLayer.
Definition at line 139 of file DEPRECATED/RBMMultinomialLayer.cc.
{ inherited::makeDeepCopyFromShallowCopy(copies); }
static StaticInitializer PLearn::RBMMultinomialLayer::_static_initializer_ [static] |
Reimplemented from PLearn::RBMLayer.
Definition at line 98 of file DEPRECATED/RBMMultinomialLayer.h.
Vec PLearn::RBMMultinomialLayer::tmp_softmax [mutable, protected] |
Definition at line 155 of file RBMMultinomialLayer.h.
Referenced by freeEnergyContributionGradient().