PLearn 0.1
|
Go to the source code of this file.
Classes | |
union | PLearn::_plearn_nan_type |
class | PLearn::PLMathInitializer |
Namespaces | |
namespace | PLearn |
< for swap | |
Defines | |
#define | MISSING_VALUE (plearn_nan.d) |
Quiet NaN (float pattern) Intel Compiler seems to have a bug when initializing a class' members with NAN. | |
#define | M_SQRT2 1.41421356237309504880 |
INFINITY is not defined under Windows, or its definition may produce a compilation warning when used. | |
#define | M_PI 3.14159265358979323846 |
Define M_PI as Pi (may not be defined on all systems). | |
#define | pl_log std::log |
#define | MIN(a, b) ((a)<(b)?(a):(b)) |
Deprecated, use std::min and std::max instead. | |
#define | MAX(a, b) ((a)>(b)?(a):(b)) |
#define | SIGN(a) ((a)>=0?1:-1) |
#define | Pi 3.141592653589793 |
#define | LogPi 1.14472988585 |
#define | Log2Pi 1.837877066409 |
#define | LOG_2 0.693147180559945 |
#define | LOG_INIT -REAL_MAX |
#define | MINUS_LOG_THRESHOLD -18.42 |
#define | DEG2RAD Pi/180.0 |
#define | RAD2DEG 57.29578 |
#define | TANHTABLESIZE 5000 |
#define | MAXTANHX 10. |
#define | DOUBLE_TO_INT(in, out) out = int(round(in)) |
#define | FSWAP(a, b) do {real _c; _c = *(a); *(a) = *(b); *(b) = _c;} while(0) |
Typedefs | |
typedef real(* | PLearn::tRealFunc )(real) |
typedef real(* | PLearn::tRealReadFunc )(real, real) |
Functions | |
real | PLearn::log_force_nan_if_negative (real a) |
Under Cygwin with GCC, log(x) with x < 0 returns -Inf instead of NaN. | |
real | PLearn::sign (real a) |
real | PLearn::positive (real a) |
real | PLearn::negative (real a) |
bool | PLearn::is_equal (real a, real b, real absolute_tolerance_threshold=1.0, real absolute_tolerance=ABSOLUTE_TOLERANCE, real relative_tolerance=RELATIVE_TOLERANCE) |
Test float equality (correctly deals with 'nan' and 'inf' values). | |
bool | PLearn::fast_is_equal (real a, real b, real absolute_tolerance_threshold=1.0, real absolute_tolerance=ABSOLUTE_TOLERANCE, real relative_tolerance=RELATIVE_TOLERANCE) |
Test float equality (but does not deal with 'nan' and 'inf' values). | |
bool | PLearn::fast_exact_is_equal (real a, real b) |
Test exact float equality. | |
bool | PLearn::fast_is_more (real a, real b, real absolute_tolerance_threshold=1.0, real absolute_tolerance=ABSOLUTE_TOLERANCE, real relative_tolerance=RELATIVE_TOLERANCE) |
Test float inequality (but does not deal with 'nan' and 'inf' values). | |
bool | PLearn::fast_is_less (real a, real b, real absolute_tolerance_threshold=1.0, real absolute_tolerance=ABSOLUTE_TOLERANCE, real relative_tolerance=RELATIVE_TOLERANCE) |
Test float inequality (but does not deal with 'nan' and 'inf' values). | |
bool | PLearn::is_more (real a, real b, real absolute_tolerance_threshold=1.0, real absolute_tolerance=ABSOLUTE_TOLERANCE, real relative_tolerance=RELATIVE_TOLERANCE) |
Test float inequality while dealling with 'nan' and 'inf' values. | |
template<class T > | |
T | PLearn::square (const T &x) |
real | PLearn::square_f (real x) |
template<class T > | |
T | PLearn::two (const T &x) |
real | PLearn::fasttanh (const real &x) |
real | PLearn::fastsigmoid (const real &x) |
real | PLearn::ultrafasttanh (const real &x) |
real | PLearn::ultrafastsigmoid (const real &x) |
real | PLearn::hinge_loss (const real &output, int target) |
real | PLearn::d_hinge_loss (const real &output, int target) |
template<class T > | |
bool | PLearn::is_missing (const T &x) |
Tells if the passed value means "missing" for its data-type. | |
bool | PLearn::is_missing (double x) |
Missing value for double and float are represented by NaN. | |
bool | PLearn::is_missing (float x) |
Missing value for double and float are represented by NaN. | |
bool | PLearn::is_integer (real x) |
real | PLearn::FABS (real x) |
real | PLearn::mypow (real x, real p) |
real | PLearn::ipow (real x, int p) |
int | PLearn::ipow (int x, int p) |
real | PLearn::sigmoid (real x) |
numerically stable version of sigmoid(x) = 1.0/(1.0+exp(-x)) | |
real | PLearn::is_positive (real x) |
"hard" version of the sigmoid, i.e. | |
real | PLearn::inverse_sigmoid (real x) |
Numerically stable version of inverse_sigmoid(x) = log(x/(1-x)). | |
real | PLearn::softplus (real x) |
numerically stable computation of log(1+exp(x)) | |
real | PLearn::tabulated_softplus (real x) |
real | PLearn::inverse_softplus (real y) |
inverse of softplus function | |
real | PLearn::hard_slope (real x, real left=0, real right=1) |
real | PLearn::log_sigmoid (real x) |
to avoid 0 or 1 probability, work in the log-domain | |
real | PLearn::soft_slope (real x, real smoothness=1, real left=0, real right=1) |
real | PLearn::tabulated_soft_slope (real x, real smoothness=1, real left=0, real right=1) |
real | PLearn::d_soft_slope (real x, real smoothness=1, real left=0, real right=1) |
int | PLearn::n_choose (int M, int N) |
Return M choose N, i.e., M! / ( N! (M-N)! ) | |
real | PLearn::safeflog (real a) |
real | PLearn::safelog (real a) |
real | PLearn::safeexp (real a) |
real | PLearn::log (real base, real a) |
real | PLearn::logtwo (real a) |
real | PLearn::safeflog (real base, real a) |
real | PLearn::safeflog2 (real a) |
real | PLearn::logadd (double log_a, double log_b) |
compute log(exp(log_a)+exp(log_b)) without losing too much precision (doing the computation in double precision) | |
real | PLearn::logsub (real log_a, real log_b) |
compute log(exp(log_a)-exp(log_b)) without losing too much precision | |
real | PLearn::dilogarithm (real x) |
It is also useful because -dilogarithm(-exp(x)) is the primitive of the softplus function log(1+exp(x)). | |
real | PLearn::softplus_primitive (real x) |
real | PLearn::tabulated_softplus_primitive (real x) |
real | PLearn::hard_slope_integral (real l, real r, real a, real b) |
real | PLearn::soft_slope_integral (real smoothness, real left, real right, real a, real b) |
real | PLearn::tabulated_soft_slope_integral (real smoothness, real left, real right, real a, real b) |
Variables | |
_plearn_nan_type | PLearn::plearn_nan |
Definition in file pl_math.h.
#define DEG2RAD Pi/180.0 |
Definition at line 178 of file pl_math.h.
Referenced by PLearn::ICP::build_(), main(), PLearn::rotationFromFixedAngles(), and PLearn::rotationMatrixFromAngles().
Definition at line 301 of file pl_math.h.
Referenced by PLearn::fast_gauss_01_quantile(), PLearn::fasttanh(), and PLearn::PLMathTest::perform().
#define LOG_2 0.693147180559945 |
Definition at line 166 of file pl_math.h.
Referenced by PLearn::logadd(), PLearn::logtwo(), and PLearn::safeflog2().
#define LOG_INIT -REAL_MAX |
Definition at line 170 of file pl_math.h.
Referenced by PLearn::logadd().
#define LogPi 1.14472988585 |
Definition at line 158 of file pl_math.h.
Referenced by PLearn::RBMGaussianLayer::freeEnergyContribution().
#define M_PI 3.14159265358979323846 |
Define M_PI as Pi (may not be defined on all systems).
Definition at line 107 of file pl_math.h.
Referenced by PLearn::GaussianProcessNLLVariable::fprop(), PLearn::logOfCompactGaussian(), and PLearn::logOfNormal().
#define M_SQRT2 1.41421356237309504880 |
INFINITY is not defined under Windows, or its definition may produce a compilation warning when used.
We instead use the STL numeric limits. Define M_SQRT2 as the square root of 2 (may not be defined on all systems).
Definition at line 102 of file pl_math.h.
Referenced by PLearn::RBMGaussianLayer::computeStdDeviation(), PLearn::GhostScript::drawCross(), and PLearn::RBMGaussianLayer::forget().
Definition at line 146 of file pl_math.h.
Referenced by PLearn::fullyRebalance2Classes(), PLearn::RowMapSparseMatrix< real >::getMaxColumnIndex(), PLearn::FinancePreprocVMatrix::getNewRow(), PLearn::max(), PLearn::TMat< pair< real, real > >::resize(), PLearn::TMat< T >::resizePreserve(), PLearn::RGBImageVMatrix::RGBImageVMatrix(), PLearn::RGBImage::shrinkToIntersection(), PLearn::SequentialModelSelector::test(), PLearn::MovingAverage::test(), PLearn::EmbeddedSequentialLearner::test(), PLearn::SequentialModelSelector::train(), PLearn::MovingAverage::train(), and PLearn::LiftStatsCollector::update().
#define MAXTANHX 10. |
Definition at line 279 of file pl_math.h.
Referenced by PLearn::fasttanh(), and PLearn::PLMathInitializer::PLMathInitializer().
Deprecated, use std::min and std::max instead.
Definition at line 142 of file pl_math.h.
Referenced by PLearn::LiftStatsCollector::computeLiftMax(), PLearn::displayHistogram(), PLearn::eigenSparseNonSymmMat(), PLearn::eigenSparseSymmMat(), PLearn::LiftStatsIterator::finish(), PLearn::FinancePreprocVMatrix::getNewRow(), PLearn::VarArray::maxUpdate(), PLearn::min(), PLearn::RGBImageVMatrix::RGBImageVMatrix(), PLearn::FieldConvertCommand::run(), PLearn::RGBImageVMatrix::setImage(), PLearn::RGBImage::shrinkToIntersection(), PLearn::SymmMatNullSpaceByInversePowerIteration(), and PLearn::ObservationWindow::update().
#define MINUS_LOG_THRESHOLD -18.42 |
Definition at line 174 of file pl_math.h.
Referenced by PLearn::logadd(), and PLearn::logsub().
#define MISSING_VALUE (plearn_nan.d) |
Quiet NaN (float pattern) Intel Compiler seems to have a bug when initializing a class' members with NAN.
Definition at line 88 of file pl_math.h.
Referenced by PLearn::VecStatsCollector::append(), PLearn::BasisSelectionRegressor::appendCandidateFunctionsOfSingleField(), PLearn::argmax(), PLearn::argmin(), PLearn::avgdev(), PLearn::StackedSVDNet::build_(), PLearn::SequentialLearner::build_(), PLearn::SelectColumnsVMatrix::build_(), PLearn::ReIndexedTargetVariable::build_(), PLearn::NLLNeighborhoodWeightsVariable::build_(), PLearn::NeuralProbabilisticLanguageModel::build_(), PLearn::NeuralNet::build_(), PLearn::MovingAverageVMatrix::build_(), PLearn::LinearInductiveTransferClassifier::build_(), PLearn::GaussianContinuumDistribution::build_(), PLearn::FeatureSetSequentialCRF::build_(), PLearn::FeatureSetNNet::build_(), PLearn::FeatureSetNaiveBayesClassifier::build_(), PLearn::DictionaryVMatrix::build_(), PLearn::CumVMatrix::build_(), PLearn::GaussMix::cdf(), PLearn::MergeDond2Files::combineAndPut(), PLearn::VPLPreprocessedLearner2::computeConfidenceFromOutput(), PLearn::VPLPreprocessedLearner::computeConfidenceFromOutput(), PLearn::PLearner::computeConfidenceFromOutput(), PLearn::VariableSelectionWithDirectedGradientDescent::computeCostsFromOutputs(), PLearn::SubsamplingDBN::computeCostsFromOutputs(), PLearn::StructuralLearner::computeCostsFromOutputs(), PLearn::StackedSVDNet::computeCostsFromOutputs(), PLearn::StackedFocusedAutoassociatorsNet::computeCostsFromOutputs(), PLearn::StackedAutoassociatorsNet::computeCostsFromOutputs(), PLearn::PseudolikelihoodRBM::computeCostsFromOutputs(), PLearn::MultiInstanceNNet::computeCostsFromOutputs(), PLearn::ManifoldParzen::computeCostsFromOutputs(), PLearn::KernelProjection::computeCostsFromOutputs(), PLearn::DiscriminativeRBM::computeCostsFromOutputs(), PLearn::DiscriminativeDeepBeliefNet::computeCostsFromOutputs(), PLearn::DeepNonLocalManifoldParzen::computeCostsFromOutputs(), PLearn::DeepBeliefNet::computeCostsFromOutputs(), PLearn::CompareLearner::computeCostsFromOutputs(), PLearn::AddCostToLearner::computeCostsFromOutputs(), PLearn::AdaBoost::computeCostsFromOutputs(), PLearn::RegressionTree::computeCostsFromOutputsAndNodes(), PLearn::MemoryCachedKernel::computeGramMatrixDerivNV(), PLearn::PLearner::computeInputOutputConfMat(), PLearn::ModuleLearner::computeOutput(), PLearn::DistRepNNet::computeOutput(), PLearn::NNet::computeOutputAndCosts(), PLearn::MultiInstanceNNet::computeOutputAndCosts(), PLearn::MultiClassAdaBoost::computeOutputAndCosts(), PLearn::ExhaustiveNearestNeighbors::computeOutputAndCosts(), PLearn::DistRepNNet::computeOutputAndCosts(), PLearn::BallTreeNearestNeighbors::computeOutputAndCosts(), PLearn::AdaBoost::computeOutputAndCosts(), PLearn::GaussianProcessRegressor::computeOutputAux(), PLearn::PLearner::computeOutputConfMat(), PLearn::PLearner::computeOutputCovMat(), PLearn::GaussianProcessRegressor::computeOutputCovMat(), PLearn::DeepBeliefNet::computeOutputsAndCosts(), PLearn::GenericNearestNeighbors::constructOutputVector(), PLearn::SDBVMFieldDateDiff::convertField(), PLearn::covariance(), PLearn::date_to_double(), PLearn::date_to_float(), PLearn::datetime_to_double(), PLearn::det(), PLearn::DichotomizeDond2DiscreteVariables::dichotomizeDiscreteVariables(), PLearn::dilogarithm(), PLearn::StatsCollector::dmode(), PLearn::ThresholdedKernel::evaluate(), PLearn::ClassErrorCostFunction::evaluate(), PLearn::ThresholdedKernel::evaluate_i_j(), PLearn::ThresholdedKernel::evaluate_i_x_again(), PLearn::ThresholdedKernel::evaluate_x_i_again(), PLearn::ProcessSymbolicSequenceVMatrix::fill_current_row(), PLearn::ManifoldParzen2::find_nearest_neighbor(), PLearn::QuantilesStatsIterator::finish(), PLearn::StatsCollector::forget(), PLearn::SequentialLearner::forget(), PLearn::SoftmaxNLLCostModule::fprop(), PLearn::RBMModule::fprop(), PLearn::OnBagsModule::fprop(), PLearn::NLLCostModule::fprop(), PLearn::LiftOutputVariable::fprop(), PLearn::LayerCostModule::fprop(), PLearn::geometric_mean(), PLearn::SelectColumnsVMatrix::get(), PLearn::MeanMedianModeImputationVMatrix::get(), PLearn::VecStatsCollector::getCovariance(), PLearn::AutoSDBVMatrix::getMappings(), PLearn::ProcessSymbolicSequenceVMatrix::getNewRow(), PLearn::MovingAverageVMatrix::getNewRow(), PLearn::MixUnlabeledNeighbourVMatrix::getNewRow(), PLearn::MissingInstructionVMatrix::getNewRow(), PLearn::MeanImputationVMatrix::getNewRow(), PLearn::DichotomizeVMatrix::getNewRow(), PLearn::DatedJoinVMatrix::getNewRow(), PLearn::AutoSDBVMatrix::getNewRow(), PLearn::AddMissingVMatrix::getNewRow(), PLearn::RegressionTreeMulticlassLeaveProb::getOutputAndError(), PLearn::RegressionTreeMulticlassLeaveFast::getOutputAndError(), PLearn::RegressionTreeMulticlassLeave::getOutputAndError(), PLearn::RegressionTreeLeave::getOutputAndError(), PLearn::TextFilesVMatrix::getPostalEncoding(), PLearn::MultiTaskSeparationSplitter::getSplit(), PLearn::VecStatsCollector::getStat(), PLearn::VMatrix::getStringVal(), PLearn::SelectColumnsVMatrix::getStringVal(), PLearn::ProcessSymbolicSequenceVMatrix::getStringVal(), PLearn::LemmatizeVMatrix::getStringVal(), PLearn::DictionaryVMatrix::getStringVal(), PLearn::SelectColumnsVMatrix::getSubRow(), PLearn::ProcessSymbolicSequenceVMatrix::getValues(), PLearn::harmonic_mean(), PLearn::GaussianContinuumDistribution::initializeParams(), PLearn::inverse_softplus(), PLearn::isOverlapping(), PLearn::PartSupervisedDBN::jointGreedyStep(), PLearn::GaussPartSupervisedDBN::jointGreedyStep(), PLearn::loadAscii(), PLearn::loadSTATLOG(), PLearn::loadUCIMLDB(), PLearn::log_force_nan_if_negative(), PLearn::matlabSave(), PLearn::mean(), PLearn::new_read_compressed(), PLearn::HyperOptimize::optimize(), PLearn::NeuralProbabilisticLanguageModel::output_gradient_verification(), PLearn::FeatureSetSequentialCRF::output_gradient_verification(), PLearn::FeatureSetNNet::output_gradient_verification(), PLearn::p_value(), PLearn::paired_t_test(), PLearn::PLMathTest::perform(), PLearn::FileVMatrixTest::perform(), PLearn::PTester::perform1Split(), PLearn::pl_isnumber(), PLearn::pl_strtod(), PLearn::StatsCollector::pseudo_quantile(), PLearn::RealMapping::read(), PLearn::PStream::readAsciiNum(), PLearn::StatsCollector::remove_observation(), PLearn::VMatLanguage::run(), PLearn::SequentialModelSelector::sequenceCost(), PLearn::SDBVMOutputCoder::setOutput(), PLearn::StatsCollector::sharperatio(), PLearn::SpearmanRankCorrelation(), PLearn::sum(), PLearn::SupervisedDBN::supervisedContrastiveDivergenceStep(), PLearn::PartSupervisedDBN::supervisedContrastiveDivergenceStep(), PLearn::GaussPartSupervisedDBN::supervisedContrastiveDivergenceStep(), PLearn::GaussMix::survival_fn(), PLearn::SubsamplingDBN::test(), PLearn::StructuralLearner::test(), PLearn::SequentialModelSelector::test(), PLearn::PseudolikelihoodRBM::test(), PLearn::DynamicallyLinkedRBMsModel::test(), PLearn::DenoisingRecurrentNet::test(), PLearn::DeepBeliefNet::test(), PLearn::RowIterator::toDouble(), PLearn::FieldValue::toDouble(), PLearn::todouble(), PLearn::TopDownAsymetricDeepNetwork::train(), PLearn::SubsamplingDBN::train(), PLearn::StructuralLearner::train(), PLearn::StackedSVDNet::train(), PLearn::StackedFocusedAutoassociatorsNet::train(), PLearn::StackedAutoassociatorsNet::train(), PLearn::PseudolikelihoodRBM::train(), PLearn::NatGradSMPNNet::train(), PLearn::NatGradNNet::train(), PLearn::mNNet::train(), PLearn::ManifoldParzen::train(), PLearn::DynamicallyLinkedRBMsModel::train(), PLearn::DiscriminativeRBM::train(), PLearn::DiscriminativeDeepBeliefNet::train(), PLearn::DenoisingRecurrentNet::train(), PLearn::DeepNonLocalManifoldParzen::train(), PLearn::DeepBeliefNet::train(), PLearn::TextFilesVMatrix::transformStringToValue(), PLearn::ToBagClassifier::updateCostAndBagOutput(), PLearn::variance(), PLearn::Function::verifyGradient(), PLearn::weighted_mean(), PLearn::weighted_variance(), and PLearn::StatsCollector::zpr1t().
#define pl_log std::log |
Definition at line 118 of file pl_math.h.
Referenced by PLearn::bnldev(), PLearn::SumEntropyOfCategoricals::bprop(), PLearn::SumEntropyOfBernoullis::bprop(), PLearn::NonLocalManifoldParzen::build_(), PLearn::NLLNeighborhoodWeightsVariable::build_(), PLearn::AsciiVMatrix::build_(), PLearn::choleskyInvert(), PLearn::compute_log(), PLearn::PseudolikelihoodRBM::compute_Z(), PLearn::VariableSelectionWithDirectedGradientDescent::computeCostsFromOutputs(), PLearn::PseudolikelihoodRBM::computeCostsFromOutputs(), PLearn::PDistribution::computeCostsFromOutputs(), PLearn::PartSupervisedDBN::computeCostsFromOutputs(), PLearn::ManifoldParzen::computeCostsFromOutputs(), PLearn::KNNClassifier::computeCostsFromOutputs(), PLearn::KFoldLogisticClassifier::computeCostsFromOutputs(), PLearn::HintonDeepBeliefNet::computeCostsFromOutputs(), PLearn::GaussPartSupervisedDBN::computeCostsFromOutputs(), PLearn::GaussianDBNClassification::computeCostsFromOutputs(), PLearn::DiscriminativeRBM::computeCostsFromOutputs(), PLearn::DeepNonLocalManifoldParzen::computeCostsFromOutputs(), PLearn::AddCostToLearner::computeCostsFromOutputs(), PLearn::RationalQuadraticARDKernel::computeGramMatrixDerivIspAlpha(), PLearn::LinearRegressor::computeInformationCriteria(), PLearn::GaussMix::computeLogLikelihood(), PLearn::ManifoldParzen::computeOutput(), PLearn::LocalGaussianClassifier::computeOutput(), PLearn::DeepNonLocalManifoldParzen::computeOutput(), PLearn::GaussMix::computePosteriors(), PLearn::RationalQuadraticARDKernel::derivIspAlpha(), PLearn::SquaredExponentialARDKernel::derivIspGlobalSigma(), PLearn::NeuralNetworkARDKernel::derivIspGlobalSigma(), PLearn::Matern1ARDKernel::derivIspGlobalSigma(), PLearn::det(), PLearn::entropy(), PLearn::GaussianDensityKernel::evaluate(), PLearn::CorrelationKernel::evaluate(), PLearn::expdev(), PLearn::NatGradSMPNNet::fbpropLoss(), PLearn::NatGradNNet::fbpropLoss(), PLearn::mNNet::fbpropLoss(), PLearn::findSmallestEigenPairOfSymmMat(), PLearn::PartSupervisedDBN::fineTuneByGradientDescent(), PLearn::HintonDeepBeliefNet::fineTuneByGradientDescent(), PLearn::GaussPartSupervisedDBN::fineTuneByGradientDescent(), PLearn::DeepNonLocalManifoldParzen::fineTuningStep(), PLearn::WeightedLogGaussian::fprop(), PLearn::SumEntropyOfCategoricals::fprop(), PLearn::SumEntropyOfBernoullis::fprop(), PLearn::NllGeneralGaussianVariable::fprop(), PLearn::NLLErrModule::fprop(), PLearn::NLLCostModule::fprop(), PLearn::NegLogPoissonVariable::fprop(), PLearn::NegCrossEntropySigmoidVariable::fprop(), PLearn::GaussianProcessNLLVariable::fprop(), PLearn::CrossEntropyVariable::fprop(), PLearn::RBMMultinomialLayer::fpropNLL(), PLearn::RBMLocalMultinomialLayer::fpropNLL(), PLearn::RBMGaussianLayer::fpropNLL(), PLearn::RBMGaussianLayer::freeEnergyContribution(), PLearn::gamdev(), PLearn::TransformationLearner::gamma_sample(), PLearn::gauss_log_density_stddev(), PLearn::gauss_log_density_var(), PLearn::gaussian_01(), PLearn::GDFindSmallEigenPairs(), PLearn::RBMTruncExpLayer::generateSample(), PLearn::RBMTruncExpLayer::generateSamples(), PLearn::geometric_mean(), PLearn::incomplete_beta(), PLearn::TransformationLearner::INIT_weight(), PLearn::inverse_sigmoid(), PLearn::inverse_softplus(), PLearn::PartSupervisedDBN::jointGreedyStep(), PLearn::GaussPartSupervisedDBN::jointGreedyStep(), PLearn::log(), PLearn::UniformDistribution::log_density(), PLearn::TransformationLearner::log_density(), PLearn::SupervisedDBN::log_density(), PLearn::PartSupervisedDBN::log_density(), PLearn::NonLocalManifoldParzen::log_density(), PLearn::NeighborhoodBoxVolumeDensityEstimator::log_density(), PLearn::MixtureDistribution::log_density(), PLearn::ManifoldKNNDistribution::log_density(), PLearn::LocallyMagnifiedDistribution::log_density(), PLearn::KernelDensityEstimator::log_density(), PLearn::HistogramDistribution::log_density(), PLearn::HintonDeepBeliefNet::log_density(), PLearn::GaussPartSupervisedDBN::log_density(), PLearn::GaussMix::log_density(), PLearn::GaussianDBNRegression::log_density(), PLearn::GaussianDBNClassification::log_density(), PLearn::ConditionalDensityNet::log_density(), PLearn::log_gamma(), PLearn::logOfCompactGaussian(), PLearn::logOfNormal(), PLearn::logtwo(), PLearn::PLMathTest::perform(), PLearn::pl_dgammlndz(), PLearn::pl_gammln(), PLearn::pl_gcf(), PLearn::pl_gser(), PLearn::poidev(), PLearn::positive_dilogarithm(), PLearn::GaussMix::precomputeGaussianLogCoefficient(), PLearn::ridgeRegressionByGCV(), PLearn::VMatLanguage::run(), PLearn::safeflog(), PLearn::GaussMix::setPredictor(), PLearn::KroneckerBaseKernel::softplusFloor(), PLearn::sum_of_log(), PLearn::SymmMatNullSpaceByInversePowerIteration(), PLearn::VariableSelectionWithDirectedGradientDescent::train(), PLearn::UnfrozenDeepBeliefNet::train(), PLearn::ClassifierFromDensity::train(), and PLearn::weightedRidgeRegressionByGCV().
#define TANHTABLESIZE 5000 |
Definition at line 278 of file pl_math.h.
Referenced by PLearn::fasttanh(), and PLearn::PLMathInitializer::PLMathInitializer().