►Cshark::AbstractBudgetMaintenanceStrategy< InputType > | This is the abstract interface for any budget maintenance strategy |
Cshark::MergeBudgetMaintenanceStrategy< InputType > | Budget maintenance strategy that merges two vectors |
Cshark::ProjectBudgetMaintenanceStrategy< InputType > | Budget maintenance strategy that projects a vector |
Cshark::RemoveBudgetMaintenanceStrategy< InputType > | Budget maintenance strategy that removes a vector |
►Cshark::AbstractBudgetMaintenanceStrategy< RealVector > | |
Cshark::MergeBudgetMaintenanceStrategy< RealVector > | Budget maintenance strategy merging vectors |
Cshark::ProjectBudgetMaintenanceStrategy< RealVector > | Budget maintenance strategy that projects a vector |
►Cshark::AbstractConstraintHandler< SearchPointType > | Implements the base class for constraint handling |
Cshark::BoxConstraintHandler< SearchPointType > | |
►Cshark::AbstractConstraintHandler< RealVector > | |
Cshark::BoxConstraintHandler< RealVector > | |
►Cshark::AbstractConstraintHandler< Vector > | |
Cshark::BoxConstraintHandler< Vector > | |
►Cshark::AbstractNearestNeighbors< InputType, LabelType > | Interface for Nearest Neighbor queries |
Cshark::SimpleNearestNeighbors< InputType, LabelType > | Brute force optimized nearest neighbor implementation |
Cshark::TreeNearestNeighbors< InputType, LabelType > | Nearest Neighbors implementation using binary trees |
Cshark::AbstractStoppingCriterion< ResultSetT > | Base class for stopping criteria of optimization algorithms |
►Cshark::AbstractStoppingCriterion< ResultSet > | |
Cshark::MaxIterations< ResultSet > | This stopping criterion stops after a fixed number of iterations |
►Cshark::AbstractStoppingCriterion< SingleObjectiveResultSet< PointType > > | |
Cshark::TrainingError< PointType > | This stopping criterion tracks the improvement of the error function of the training error over an interval of iterations |
Cshark::TrainingProgress< PointType > | This stopping criterion tracks the improvement of the training error over an interval of iterations |
►Cshark::AbstractStoppingCriterion< SingleObjectiveResultSet< RealVector > > | |
Cshark::ValidatedStoppingCriterion | Given the current Result set of the optimizer, calculates the validation error using a validation function and hands the results over to the underlying stopping criterion |
►Cshark::AbstractStoppingCriterion< ValidatedSingleObjectiveResultSet< PointType > > | |
Cshark::GeneralizationLoss< PointType > | The generalization loss calculates the relative increase of the validation error compared to the minimum training error |
Cshark::GeneralizationQuotient< PointType > | SStopping criterion monitoring the quotient of generalization loss and training progress |
Cshark::AdditiveEpsilonIndicator | Implements the Additive approximation properties of sets |
Cshark::BarsAndStripes | Generates the Bars-And-Stripes problem. In this problem, a 4x4 image has either rows or columns of the same value |
Cshark::BaseDCNonDominatedSort | Divide-and-conquer algorithm for non-dominated sorting |
►Cshark::statistics::BaseStatisticsObject | Base class for all Statistic Objects to be used with Statistics |
Cshark::statistics::FractionMissing | For a vector of points computes for every dimension the fraction of missing values |
Cshark::statistics::Mean | For a vector of points computes for every dimension the mean |
►Cshark::statistics::Quantile | For a vector of points computes for every dimension the p-quantile |
Cshark::statistics::LowerQuantile | For a vector of points computes for every dimension the 25%-quantile |
Cshark::statistics::Median | For a vector of points computes for every dimension the median |
Cshark::statistics::UpperQuantile | For a vector of points computes for every dimension the 75%-quantile |
Cshark::statistics::Variance | For a vector of points computes for every dimension the variance |
Cshark::Batch< shark::blas::compressed_vector< T > > | Specialization for ublas compressed vectors which are compressed matrices in batch mode! |
Cshark::BatchTraits< BatchType > | |
Cshark::BatchTraits< blas::compressed_matrix< T > > | |
Cshark::BatchTraits< blas::dense_matrix_adaptor< T, blas::row_major > > | |
Cshark::BatchTraits< blas::matrix< T > > | |
Cshark::BatchTraits< WeightedDataBatch< DataType, WeightType > > | |
Cshark::BiasSolver< Matrix > | |
Cshark::BiasSolverSimplex< Matrix > | |
►Cshark::BinaryTree< InputT > | Super class of binary space-partitioning trees |
Cshark::KDTree< InputT > | KD-tree, a binary space-partitioning tree |
►Cshark::BinaryTree< Container::value_type > | |
Cshark::KHCTree< Container, CuttingAccuracy > | KHC-tree, a binary space-partitioning tree |
►Cshark::BinaryTree< VectorType > | |
Cshark::LCTree< VectorType, CuttingAccuracy > | LC-tree, a binary space-partitioning tree |
Cshark::BitflipMutator | Bitflip mutation operator |
Cshark::BlockMatrix2x2< Matrix > | SVM regression matrix |
Cshark::BoxConstrainedProblem< SVMProblem > | Quadratic program with box constraints |
►Cshark::BoxConstrainedProblem< Problem > | |
►Cshark::BoxBasedShrinkingStrategy< BoxConstrainedProblem< Problem > > | |
Cshark::BoxConstrainedShrinkingProblem< Problem > | |
Cshark::BoxedSVMProblem< MatrixT > | Boxed problem for alpha in [lower,upper]^n and equality constraints |
Cshark::CachedMatrix< Matrix > | Efficient quadratic matrix cache |
Cshark::CanBeCalled< Functor, Argument > | Detects whether Functor(Argument) can be called |
Cshark::CanBeCalled< R(*)(T), Argument > | |
Cshark::CanBeCalled< R(T), Argument > | |
Cshark::CMAChromosome | Models a CMAChromosomeof the elitist (MO-)CMA-ES that encodes strategy parameters |
Cshark::ConstProxyReference< T > | Sets the type of ProxxyReference |
Cshark::CrowdingDistance | Implements the Crowding Distance of a pareto front |
Cshark::CSVMProblem< MatrixT > | Problem formulation for binary C-SVM problems |
Cshark::CVFolds< DatasetTypeT > | |
Cshark::CVFolds< DatasetType > | |
Cshark::CVFolds< LabeledData< InputType, unsigned int > > | |
Cshark::DataDistribution< InputType > | A DataDistribution defines an unsupervised learning problem |
►Cshark::DataDistribution< RealVector > | |
Cshark::ImagePatches | Given a set of images, draws a set of image patches of a given size |
Cshark::NormalDistributedPoints | Generates a set of normally distributed points |
Cshark::DataView< DatasetType > | Constant time Element-Lookup for Datasets |
Cshark::DataView< const shark::LabeledData > | |
Cshark::DataView< LabeledData< InputType, LabelType > const > | |
Cshark::DataView< shark::Data< InputType > const > | |
Cshark::DataView< shark::Data< LabelType > const > | |
Cshark::DifferenceKernelMatrix< InputType, CacheType > | SVM ranking matrix |
Cshark::tags::DiscreteSpace | A Tag for EnumerationSpaces. It tells the Functions, that the space is discrete and can be enumerated |
Cshark::DistantModes | Creates a set of pattern (each later representing a mode) which than are randomly perturbed to create the data set. The dataset was introduced in Desjardins et al. (2010) (Parallel Tempering for training restricted Boltzmann machines, AISTATS 2010) |
Cshark::DoublePole | |
Cshark::ElitistSelection< Ordering > | Survival selection to find the next parent set |
Cshark::Energy< RBM > | The Energy function determining the Gibbs distribution of an RBM |
Cshark::EnergyStoringTemperedMarkovChain< Operator > | Implements parallel tempering but also stores additional statistics on the energy differences |
Cshark::QpSparseArray< QpFloatType >::Entry | Non-default (non-zero) array entry |
Cshark::EPTournamentSelection< Ordering > | Survival and mating selection to find the next parent set |
Cshark::QpMcSimplexDecomp< Matrix >::Example | Data structure describing one training example |
Cshark::QpMcBoxDecomp< Matrix >::Example | Data structure describing one training example |
Cshark::ExampleModifiedKernelMatrix< InputType, CacheType > | |
►Cstd::exception | STL class |
►Cshark::Exception | Top-level exception class of the shark library |
Cshark::TypedFeatureNotAvailableException< Feature > | Exception indicating the attempt to use a feature which is not supported |
Cshark::FastSigmoidNeuron | Fast sigmoidal function, which does not need to compute an exponential function |
Cshark::Individual< PointType, FitnessTypeT, Chromosome >::FitnessOrdering | Ordering relation by the fitness of the individuals(only single objective) |
Cshark::GaussianKernelMatrix< T, CacheType > | Efficient special case if the kernel is Gaussian and the inputs are sparse vectors |
Cshark::GeneralQuadraticProblem< MatrixT > | Quadratic Problem with only Box-Constraints Let K the kernel matrix, than the problem has the form |
Cshark::GibbsOperator< RBMType > | Implements Block Gibbs Sampling related transition operators for various temperatures |
Cshark::HMGSelectionCriterion | |
Cshark::HypervolumeApproximator | Implements an FPRAS for approximating the volume of a set of high-dimensional objects. The algorithm is described in |
Cshark::HypervolumeCalculator | Frontend for hypervolume calculation algorithms in m dimensions |
Cshark::HypervolumeCalculator2D | Implementation of the exact hypervolume calculation in 2 dimensions |
Cshark::HypervolumeCalculator3D | Implementation of the exact hypervolume calculation in 3 dimensions |
Cshark::HypervolumeCalculatorMDHOY | Implementation of the exact hypervolume calculation in m dimensions |
Cshark::HypervolumeCalculatorMDWFG | Implementation of the exact hypervolume calculation in m dimensions |
Cshark::HypervolumeContribution | Frontend for hypervolume contribution algorithms in m dimensions |
Cshark::HypervolumeContribution2D | Finds the smallest/largest Contributors given 2D points |
Cshark::HypervolumeContribution3D | Finds the hypervolume contribution for points in 3DD |
Cshark::HypervolumeContributionApproximator | Approximately determines the point of a set contributing the least hypervolume |
Cshark::HypervolumeContributionMD | Finds the hypervolume contribution for points in MD |
Cshark::HypervolumeIndicator | Calculates the hypervolume covered by a front of non-dominated points |
Cshark::HypervolumeSubsetSelection2D | Implementation of the exact hypervolume subset selection algorithm in 2 dimensions |
►Cshark::INameable | This class is an interface for all objects which can have a name |
►Cshark::AbstractClustering< RealVector > | |
Cshark::Centroids | Clusters defined by centroids |
►Cshark::AbstractCost< LabelType, LabelType > | |
►Cshark::AbstractLoss< LabelType, LabelType > | |
Cshark::ZeroOneLoss< LabelType, OutputType > | 0-1-loss for classification |
►Cshark::AbstractCost< LabelType, OutputType > | |
►Cshark::AbstractLoss< LabelType, OutputType > | |
Cshark::SquaredLoss< OutputType, LabelType > | Squared loss for regression and classification |
Cshark::NegativeAUC< LabelType, OutputType > | Negative area under the curve |
Cshark::NegativeWilcoxonMannWhitneyStatistic< LabelType, OutputType > | Negative Wilcoxon-Mann-Whitney statistic |
►Cshark::AbstractCost< RealVector, RealVector > | |
►Cshark::AbstractLoss< RealVector, RealVector > | |
Cshark::EpsilonHingeLoss | Hinge-loss for large margin regression |
Cshark::HuberLoss | Huber-loss for for robust regression |
Cshark::SquaredEpsilonHingeLoss | Hinge-loss for large margin regression using th squared two-norm |
Cshark::TukeyBiweightLoss | Tukey's Biweight-loss for robust regression |
►Cshark::AbstractCost< Sequence, Sequence > | |
►Cshark::AbstractLoss< Sequence, Sequence > | |
Cshark::SquaredLoss< Sequence, Sequence > | |
►Cshark::AbstractCost< unsigned int, OutputType > | |
►Cshark::AbstractLoss< unsigned int, OutputType > | |
Cshark::SquaredLoss< OutputType, unsigned int > | |
►Cshark::AbstractCost< unsigned int, RealVector > | |
►Cshark::AbstractLoss< unsigned int, RealVector > | |
Cshark::CrossEntropy | Error measure for classification tasks that can be used as the objective function for training |
Cshark::HingeLoss | Hinge-loss for large margin classification |
Cshark::SquaredHingeLoss | Squared Hinge-loss for large margin classification |
Cshark::ZeroOneLoss< unsigned int, RealVector > | 0-1-loss for classification |
►Cshark::AbstractCost< unsigned int, unsigned int > | |
►Cshark::AbstractLoss< unsigned int, unsigned int > | |
Cshark::DiscreteLoss | Flexible loss for classification |
►Cshark::AbstractCost< VectorType, VectorType > | |
►Cshark::AbstractLoss< VectorType, VectorType > | |
Cshark::AbsoluteLoss< VectorType > | Absolute loss |
►Cshark::AbstractMetric< Batch< InputType >::type > | |
►Cshark::AbstractKernelFunction< Batch< InputType >::type > | |
Cshark::PointSetKernel< InputType > | Normalized version of a kernel function |
►Cshark::AbstractMetric< InputType > | |
►Cshark::AbstractKernelFunction< InputType > | |
Cshark::ARDKernelUnconstrained< InputType > | Automatic relevance detection kernel for unconstrained parameter optimization |
Cshark::GaussianRbfKernel< InputType > | Gaussian radial basis function kernel |
Cshark::LinearKernel< InputType > | Linear Kernel, parameter free |
Cshark::ModelKernel< InputType > | Kernel function that uses a Model as transformation function for another kernel |
Cshark::MonomialKernel< InputType > | Monomial kernel. Calculates \( \left\langle x_1, x_2 \right\rangle^m_exponent \) |
Cshark::NormalizedKernel< InputType > | Normalized version of a kernel function |
Cshark::PolynomialKernel< InputType > | Polynomial kernel |
Cshark::ProductKernel< InputType > | Product of kernel functions |
Cshark::ScaledKernel< InputType > | Scaled version of a kernel function |
►Cshark::WeightedSumKernel< InputType > | Weighted sum of kernel functions |
Cshark::MklKernel< InputType > | Weighted sum of kernel functions |
►Cshark::AbstractMetric< MultiTaskSample< InputTypeT > > | |
►Cshark::AbstractKernelFunction< MultiTaskSample< InputTypeT > > | |
►Cshark::ProductKernel< MultiTaskSample< InputTypeT > > | |
Cshark::MultiTaskKernel< InputTypeT > | Special kernel function for multi-task and transfer learning |
►Cshark::AbstractMetric< std::size_t > | |
►Cshark::AbstractKernelFunction< std::size_t > | |
►Cshark::DiscreteKernel | Kernel on a finite, discrete space |
Cshark::GaussianTaskKernel< InputTypeT > | Special "Gaussian-like" kernel function on tasks |
►Cshark::AbstractModel< CARTree< LabelType > ::InputType, RealVector, CARTree< LabelType > ::ParameterVectorType > | |
►Cshark::MeanModel< CARTree< LabelType > > | |
►Cshark::detail::RFClassifierBase< LabelType > | |
Cshark::RFClassifier< LabelType > | Random Forest Classifier |
►Cshark::AbstractModel< CARTree< unsigned int > ::InputType, RealVector, CARTree< unsigned int > ::ParameterVectorType > | |
Cshark::MeanModel< CARTree< unsigned int > > | |
►Cshark::AbstractModel< detail::BaseNearestNeighbor< InputType, unsigned int > ::InputType, unsigned int > | |
►Cshark::Classifier< detail::BaseNearestNeighbor< InputType, unsigned int > > | |
Cshark::NearestNeighborModel< InputType, unsigned int > | |
►Cshark::AbstractModel< InputT, OutputT > | |
Cshark::ClusteringModel< InputT, OutputT > | Abstract model with associated clustering object |
►Cshark::AbstractModel< InputT, RealVector > | |
►Cshark::ClusteringModel< InputT, RealVector > | |
Cshark::SoftClusteringModel< InputT > | Model for "soft" clustering |
►Cshark::AbstractModel< InputT, unsigned int > | |
►Cshark::ClusteringModel< InputT, unsigned int > | |
Cshark::HardClusteringModel< InputT > | Model for "hard" clustering |
►Cshark::AbstractModel< InputType, blas::vector< InputType::value_type, InputType::device_type >, blas::vector< InputType::value_type, InputType::device_type > > | |
Cshark::LinearModel< InputType, ActivationFunction > | Linear Prediction with optional activation function |
►Cshark::AbstractModel< InputType, RealVector > | |
►Cshark::detail::BaseNearestNeighbor< InputType, LabelType > | |
Cshark::NearestNeighborModel< InputType, LabelType > | NearestNeighbor model for classification and regression |
►Cshark::KernelExpansion< InputType > | Linear model in a kernel feature space |
Cshark::MissingFeaturesKernelExpansion< InputType > | Kernel expansion with missing features support |
►Cshark::AbstractModel< InputType, unsigned int, VectorType > | |
Cshark::OneVersusOneClassifier< InputType, VectorType > | One-versus-one Classifier |
►Cshark::AbstractModel< KernelExpansion< InputType > ::InputType, unsigned int > | |
►Cshark::Classifier< KernelExpansion< InputType > > | |
Cshark::KernelClassifier< InputType > | Linear classifier in a kernel feature space |
►Cshark::AbstractModel< LinearModel< VectorType > ::InputType, unsigned int > | |
►Cshark::Classifier< LinearModel< VectorType > > | |
Cshark::LinearClassifier< VectorType > | Basic linear classifier |
►Cshark::AbstractModel< MeanModel< CARTree< unsigned int > > ::InputType, unsigned int > | |
Cshark::Classifier< MeanModel< CARTree< unsigned int > > > | |
►Cshark::AbstractModel< Model::InputType, unsigned int > | |
Cshark::Classifier< Model > | Conversion of real-valued or vector valued outputs to class labels |
►Cshark::AbstractModel< ModelType::InputType, RealVector, ModelType::ParameterVectorType > | |
Cshark::MeanModel< ModelType > | Calculates the weighted mean of a set of models |
►Cshark::AbstractModel< RealVector, LabelType > | |
Cshark::CARTree< LabelType > | Classification and Regression Tree |
►Cshark::AbstractModel< RealVector, RealVector > | |
Cshark::CMACMap | Linear combination of piecewise constant functions |
Cshark::RBFLayer | Implements a layer of radial basis functions in a neural network |
Cshark::RBM< VisibleLayerT, HiddenLayerT, randomT > | Stub for the RBM class. at the moment it is just a holder of the parameter set and the Energy |
►Cshark::AbstractModel< RealVector, unsigned int > | |
Cshark::CARTree< unsigned int > | |
►Cshark::AbstractModel< VectorType, blas::vector< VectorType ::value_type, VectorType ::device_type >, blas::vector< VectorType ::value_type, VectorType ::device_type > > | |
Cshark::LinearModel< VectorType > | |
►Cshark::AbstractModel< VectorType, VectorType > | |
Cshark::Normalizer< VectorType > | "Diagonal" linear model for data normalization |
►Cshark::AbstractModel< VectorType, VectorType, VectorType > | |
Cshark::ConcatenatedModel< VectorType > | ConcatenatedModel concatenates two models such that the output of the first model is input to the second |
Cshark::Conv2DModel< VectorType, ActivationFunction > | Convolutional Model for 2D image data |
Cshark::DropoutLayer< VectorType > | |
Cshark::NeuronLayer< NeuronType, VectorType > | |
►Cshark::AbstractObjectiveFunction< RealVector, double > | |
Cshark::Cigar | Convex quadratic benchmark function with single dominant axis |
Cshark::CrossValidationError< ModelTypeT, LabelTypeT > | Cross-validation error for selection of hyper-parameters |
Cshark::DiffPowers | |
Cshark::Discus | Convex quadratic benchmark function |
Cshark::Ellipsoid | Convex quadratic benchmark function |
Cshark::KernelTargetAlignment< InputType, LabelType > | Kernel Target Alignment - a measure of alignment of a kernel Gram matrix with labels |
Cshark::LooError< ModelTypeT, LabelType > | Leave-one-out error objective function |
Cshark::LooErrorCSvm< InputType, CacheType > | Leave-one-out error, specifically optimized for C-SVMs |
Cshark::MarkovPole< HiddenNeuron, OutputNeuron > | |
Cshark::NegativeGaussianProcessEvidence< InputType, OutputType, LabelType > | Evidence for model selection of a regularization network/Gaussian process |
Cshark::NegativeLogLikelihood | Computes the negative log likelihood of a dataset under a model |
Cshark::OneNormRegularizer | One-norm of the input as an objective function |
Cshark::RadiusMarginQuotient< InputType, CacheType > | Radius margin quotions for binary SVMs |
Cshark::Schwefel | Convex benchmark function |
Cshark::TwoNormRegularizer | Two-norm of the input as an objective function |
Cshark::VariationalAutoencoderError | Computes the variational autoencoder error function |
►Cshark::AbstractObjectiveFunction< SearchSpaceType, ResultT > | |
Cshark::CombinedObjectiveFunction< SearchSpaceType, ResultT > | Linear combination of objective functions |
►Cshark::AbstractOptimizer< PointType, double, SingleObjectiveResultSet< PointType > > | |
Cshark::AbstractSingleObjectiveOptimizer< PointType > | Base class for all single objective optimizer |
►Cshark::AbstractOptimizer< PointTypeT, RealVector, std::vector< ResultSet< PointTypeT, RealVector > > > | |
Cshark::AbstractMultiObjectiveOptimizer< PointTypeT > | Base class for abstract multi-objective optimizers for arbitrary search spaces |
►Cshark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > > | |
►Cshark::AbstractSingleObjectiveOptimizer< RealVector > | |
►Cshark::AbstractLineSearchOptimizer | Basis class for line search methods |
Cshark::BFGS | Broyden, Fletcher, Goldfarb, Shannon algorithm for unconstraint optimization |
Cshark::CG | Conjugate-gradient method for unconstrained optimization |
Cshark::LBFGS | Limited-Memory Broyden, Fletcher, Goldfarb, Shannon algorithm |
Cshark::Adam | Adaptive Moment Estimation Algorithm (ADAM) |
Cshark::CMA | Implements the CMA-ES |
Cshark::CMSA | Implements the CMSA |
Cshark::CrossEntropyMethod | Implements the Cross Entropy Method |
Cshark::ElitistCMA | Implements the elitist CMA-ES |
Cshark::GridSearch | Optimize by trying out a grid of configurations |
Cshark::LMCMA | Implements a Limited-Memory-CMA |
Cshark::NestedGridSearch | Nested grid search |
Cshark::PointSearch | Optimize by trying out predefined configurations |
►Cshark::RpropMinus | This class offers methods for the usage of the Resilient-Backpropagation-algorithm without weight-backtracking |
Cshark::IRpropMinus | This class offers methods for the usage of the improved Resilient-Backpropagation-algorithm without weight-backtracking |
►Cshark::RpropPlus | This class offers methods for the usage of the Resilient-Backpropagation-algorithm with weight-backtracking |
Cshark::IRpropPlus | This class offers methods for the usage of the improved Resilient-Backpropagation-algorithm with weight-backtracking |
Cshark::IRpropPlusFull | |
Cshark::SimplexDownhill | Simplex Downhill Method |
Cshark::SteepestDescent | Standard steepest descent |
Cshark::TrustRegionNewton | Simple Trust-Region method based on the full Hessian matrix |
Cshark::VDCMA | |
►Cshark::AbstractOptimizer< RealVector, RealVector, std::vector< ResultSet< RealVector, RealVector > > > | |
►Cshark::AbstractMultiObjectiveOptimizer< RealVector > | |
►Cshark::IndicatorBasedRealCodedNSGAII< NSGA3Indicator > | |
Cshark::RealCodedNSGAIII | Implements the NSGA-III |
Cshark::IndicatorBasedMOCMA< Indicator > | Implements the generational MO-CMA-ES |
Cshark::IndicatorBasedRealCodedNSGAII< Indicator > | Implements the NSGA-II |
Cshark::IndicatorBasedSteadyStateMOCMA< Indicator > | Implements the \((\mu+1)\)-MO-CMA-ES |
Cshark::MOEAD | Implements the MOEA/D algorithm |
Cshark::RVEA | Implements the RVEA algorithm |
Cshark::SMSEMOA | Implements the SMS-EMOA |
►Cshark::AbstractTrainer< KernelClassifier< InputType > > | |
Cshark::KernelBudgetedSGDTrainer< InputType, CacheType > | Budgeted stochastic gradient descent training for kernel-based models |
Cshark::KernelSGDTrainer< InputType, CacheType > | Generic stochastic gradient descent training for kernel-based models |
►Cshark::AbstractTrainer< KernelClassifier< InputType >, typename KernelClassifier< InputType > ::OutputType > | |
►Cshark::AbstractWeightedTrainer< KernelClassifier< InputType > > | |
►Cshark::AbstractSvmTrainer< InputType, unsigned int, KernelClassifier< InputType >, AbstractWeightedTrainer< KernelClassifier< InputType > > > | |
Cshark::CSvmTrainer< InputType, CacheType > | Training of C-SVMs for binary classification |
►Cshark::AbstractTrainer< KernelClassifier< InputType >, unsigned int > | |
►Cshark::AbstractWeightedTrainer< KernelClassifier< InputType >, unsigned int > | |
Cshark::KernelMeanClassifier< InputType > | Kernelized mean-classifier |
Cshark::Perceptron< InputType > | Perceptron online learning algorithm |
Cshark::AbstractTrainer< KernelExpansion< InputType >, RealVector > | |
Cshark::AbstractTrainer< KernelExpansion< InputType >, unsigned int > | |
►Cshark::AbstractTrainer< LinearClassifier< InputType >, unsigned int > | |
►Cshark::AbstractLinearSvmTrainer< InputType > | Super class of all linear SVM trainers |
Cshark::LinearCSvmTrainer< InputType > | |
Cshark::SquaredHingeLinearCSvmTrainer< InputType > | |
►Cshark::AbstractTrainer< LinearClassifier< InputVectorType >, typename LinearClassifier< InputVectorType > ::OutputType > | |
►Cshark::AbstractWeightedTrainer< LinearClassifier< InputVectorType > > | |
Cshark::LogisticRegression< InputVectorType > | Trainer for Logistic regression |
►Cshark::AbstractTrainer< LinearClassifier<>, unsigned int > | |
►Cshark::AbstractWeightedTrainer< LinearClassifier<>, unsigned int > | |
Cshark::LDA | Linear Discriminant Analysis (LDA) |
►Cshark::AbstractTrainer< LinearModel< InputVectorType > > | |
Cshark::LassoRegression< InputVectorType > | LASSO Regression |
►Cshark::AbstractTrainer< LinearModel<> > | |
Cshark::LinearRegression | Linear Regression |
►Cshark::AbstractTrainer< LinearModel<>, unsigned int > | |
Cshark::FisherLDA | Fisher's Linear Discriminant Analysis for data compression |
Cshark::AbstractTrainer< MissingFeaturesKernelExpansion< InputType >, unsigned int > | |
►Cshark::AbstractTrainer< RFClassifier< RealVector >, typename RFClassifier< RealVector > ::OutputType > | |
►Cshark::AbstractWeightedTrainer< RFClassifier< RealVector > > | |
Cshark::RFTrainer< RealVector > | |
►Cshark::AbstractTrainer< RFClassifier< unsigned int >, typename RFClassifier< unsigned int > ::OutputType > | |
►Cshark::AbstractWeightedTrainer< RFClassifier< unsigned int > > | |
Cshark::RFTrainer< unsigned int > | |
►Cshark::AbstractUnsupervisedTrainer< KernelExpansion< InputType > > | |
Cshark::OneClassSvmTrainer< InputType, CacheType > | Training of one-class SVMs |
►Cshark::AbstractUnsupervisedTrainer< LinearModel< RealVector > > | |
Cshark::NormalizeComponentsWhitening | Train a linear model to whiten the data |
Cshark::NormalizeComponentsZCA | Train a linear model to whiten the data |
►Cshark::AbstractUnsupervisedTrainer< LinearModel<> > | |
Cshark::PCA | Principal Component Analysis |
►Cshark::AbstractUnsupervisedTrainer< Normalizer< DataType > > | |
Cshark::NormalizeComponentsUnitInterval< DataType > | Train a model to normalize the components of a dataset to fit into the unit inverval |
Cshark::NormalizeComponentsUnitVariance< DataType > | Train a linear model to normalize the components of a dataset to unit variance, and optionally to zero mean |
►Cshark::AbstractUnsupervisedTrainer< ScaledKernel< InputType > > | |
Cshark::NormalizeKernelUnitVariance< InputType > | Determine the scaling factor of a ScaledKernel so that it has unit variance in feature space one on a given dataset |
►Cshark::AbstractClustering< InputT > | Base class for clustering |
Cshark::HierarchicalClustering< InputT > | Clusters defined by a binary space partitioning tree |
►Cshark::AbstractCost< LabelT, OutputT > | Cost function interface |
Cshark::AbstractLoss< LabelT, OutputT > | Loss function interface |
►Cshark::AbstractMetric< InputTypeT > | |
Cshark::AbstractKernelFunction< InputTypeT > | Base class of all Kernel functions |
Cshark::AbstractModel< InputTypeT, OutputTypeT, ParameterType > | Base class for all Models |
►Cshark::AbstractObjectiveFunction< PointType, ResultT > | Super class of all objective functions for optimization and learning |
Cshark::Ackley | Convex quadratic benchmark function with single dominant axis |
Cshark::CigarDiscus | Convex quadratic benchmark function |
Cshark::CIGTAB1 | Multi-objective optimization benchmark function CIGTAB 1 |
Cshark::CIGTAB2 | Multi-objective optimization benchmark function CIGTAB 2 |
Cshark::ConstrainedSphere | Constrained Sphere function |
Cshark::ContrastiveDivergence< Operator > | Implements k-step Contrastive Divergence described by Hinton et al. (2006) |
Cshark::DTLZ1 | Implements the benchmark function DTLZ1 |
Cshark::DTLZ2 | Implements the benchmark function DTLZ2 |
Cshark::DTLZ3 | Implements the benchmark function DTLZ3 |
Cshark::DTLZ4 | Implements the benchmark function DTLZ4 |
Cshark::DTLZ5 | Implements the benchmark function DTLZ5 |
Cshark::DTLZ6 | Implements the benchmark function DTLZ6 |
Cshark::DTLZ7 | Implements the benchmark function DTLZ7 |
Cshark::ELLI1 | Multi-objective optimization benchmark function ELLI1 |
Cshark::ELLI2 | Multi-objective optimization benchmark function ELLI2 |
Cshark::ErrorFunction | Objective function for supervised learning |
Cshark::EvaluationArchive< PointType, ResultT > | Objective function wrapper storing all function evaluations |
Cshark::ExactGradient< RBMType > | |
Cshark::Fonseca | Bi-objective real-valued benchmark function proposed by Fonseca and Flemming |
Cshark::GSP | Real-valued benchmark function with two objectives |
Cshark::Himmelblau | Multi-modal two-dimensional continuous Himmelblau benchmark function |
Cshark::IHR1 | Multi-objective optimization benchmark function IHR1 |
Cshark::IHR2 | Multi-objective optimization benchmark function IHR 2 |
Cshark::IHR3 | Multi-objective optimization benchmark function IHR3 |
Cshark::IHR4 | Multi-objective optimization benchmark function IHR 4 |
Cshark::IHR6 | Multi-objective optimization benchmark function IHR 6 |
Cshark::LZ1 | Multi-objective optimization benchmark function LZ1 |
Cshark::LZ2 | Multi-objective optimization benchmark function LZ2 |
Cshark::LZ3 | Multi-objective optimization benchmark function LZ3 |
Cshark::LZ4 | Multi-objective optimization benchmark function LZ4 |
Cshark::LZ5 | Multi-objective optimization benchmark function LZ5 |
Cshark::LZ6 | Multi-objective optimization benchmark function LZ6 |
Cshark::LZ7 | Multi-objective optimization benchmark function LZ7 |
Cshark::LZ8 | Multi-objective optimization benchmark function LZ8 |
Cshark::LZ9 | |
Cshark::MergeBudgetMaintenanceStrategy< RealVector >::MergingProblemFunction | |
Cshark::MultiChainApproximator< MarkovChainType > | Approximates the gradient by taking samples from an ensemble of Markov chains running in parallel |
Cshark::MultiObjectiveBenchmark< Objectives > | Creates a multi-objective Benchmark from a set of given single objective functions |
Cshark::NonMarkovPole | Objective function for single and double non-Markov poles |
Cshark::Rosenbrock | Generalized Rosenbrock benchmark function |
Cshark::RotatedObjectiveFunction | Rotates an objective function using a randomly initialized rotation |
Cshark::SingleChainApproximator< MarkovChainType > | Approximates the gradient by taking samples from a single Markov chain |
Cshark::Sphere | Convex quadratic benchmark function |
Cshark::SvmLogisticInterpretation< InputType > | Maximum-likelihood model selection score for binary support vector machines |
Cshark::ZDT1 | Multi-objective optimization benchmark function ZDT1 |
Cshark::ZDT2 | Multi-objective optimization benchmark function ZDT2 |
Cshark::ZDT3 | Multi-objective optimization benchmark function ZDT3 |
Cshark::ZDT4 | Multi-objective optimization benchmark function ZDT4 |
Cshark::ZDT6 | Multi-objective optimization benchmark function ZDT6 |
Cshark::AbstractOptimizer< PointType, ResultT, SolutionTypeT > | An optimizer that optimizes general objective functions |
►Cshark::AbstractTrainer< Model, LabelTypeT > | Superclass of supervised learning algorithms |
►Cshark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > > | |
Cshark::EpsilonSvmTrainer< InputType, CacheType > | Training of Epsilon-SVMs for regression |
Cshark::RegularizationNetworkTrainer< InputType > | Training of a regularization network |
►Cshark::AbstractSvmTrainer< InputType, unsigned int > | |
Cshark::SquaredHingeCSvmTrainer< InputType, CacheType > | |
►Cshark::AbstractSvmTrainer< InputType, unsigned int, KernelExpansion< InputType > > | |
Cshark::RankingSvmTrainer< InputType, CacheType > | Training of an SVM for ranking |
►Cshark::AbstractSvmTrainer< InputType, unsigned int, MissingFeaturesKernelExpansion< InputType > > | |
Cshark::MissingFeatureSvmTrainer< InputType, CacheType > | Trainer for binary SVMs natively supporting missing features |
►Cshark::AbstractWeightedTrainer< Model, LabelTypeT > | Superclass of weighted supervised learning algorithms |
Cshark::LinearSAGTrainer< InputType, LabelType > | Stochastic Average Gradient Method for training of linear models, |
Cshark::OptimizationTrainer< Model, LabelTypeT > | Wrapper for training schemes based on (iterative) optimization |
►Cshark::AbstractUnsupervisedTrainer< Model > | Superclass of unsupervised learning algorithms |
Cshark::AbstractWeightedUnsupervisedTrainer< Model > | Superclass of weighted unsupervised learning algorithms |
Cshark::CSvmDerivative< InputType, CacheType > | This class provides two main member functions for computing the derivative of a C-SVM hypothesis w.r.t. its hyperparameters. The constructor takes a pointer to a KernelClassifier and an SvmTrainer, in the assumption that the former was trained by the latter. It heavily accesses their members to calculate the derivative of the alpha and offset values w.r.t. the SVM hyperparameters, that is, the regularization parameter C and the kernel parameters. This is done in the member function prepareCSvmParameterDerivative called by the constructor. After this initial, heavier computation step, modelCSvmParameterDerivative can be called on an input sample to the SVM model, and the method will yield the derivative of the hypothesis w.r.t. the SVM hyperparameters |
Cshark::LabelOrder | This will normalize the labels of a given dataset to 0..N-1 |
Cshark::IndicatorBasedSelection< Indicator > | Implements the well-known indicator-based selection strategy |
Cshark::IndicatorBasedSelection< NSGA3Indicator > | |
Cshark::IndicatorBasedSelection< shark::HypervolumeIndicator > | |
Cshark::Individual< PointType, FitnessTypeT, Chromosome > | Individual is a simple templated class modelling an individual that acts as a candidate solution in an evolutionary algorithm |
►Cshark::Individual< RealVector, double, CMAChromosome > | |
Cshark::CMAIndividual< double > | |
►Cshark::Individual< RealVector, FitnessType, CMAChromosome > | |
Cshark::CMAIndividual< FitnessType > | |
►CInnerKernel | |
Cshark::SubrangeKernel< InputType, InnerKernel > | Weighted sum of kernel functions |
►Cshark::CrossEntropyMethod::INoiseType | Interface class for noise type |
Cshark::CrossEntropyMethod::ConstantNoise | Constant noise term z_t = noise |
Cshark::CrossEntropyMethod::LinearNoise | Linear noise term z_t = a + t / b |
►Cshark::IParameterizable< VectorType > | Top level interface for everything that holds parameters |
Cshark::AbstractModel< InputType, unsigned int, VectorType > | |
Cshark::AbstractModel< VectorType, VectorType, VectorType > | |
►Cshark::IParameterizable< blas::vector< InputType::value_type, InputType::device_type > > | |
Cshark::AbstractModel< InputType, blas::vector< InputType::value_type, InputType::device_type >, blas::vector< InputType::value_type, InputType::device_type > > | |
►Cshark::IParameterizable< blas::vector< VectorType ::value_type, VectorType ::device_type > > | |
Cshark::AbstractModel< VectorType, blas::vector< VectorType ::value_type, VectorType ::device_type >, blas::vector< VectorType ::value_type, VectorType ::device_type > > | |
►Cshark::IParameterizable< CARTree< LabelType > ::ParameterVectorType > | |
Cshark::AbstractModel< CARTree< LabelType > ::InputType, RealVector, CARTree< LabelType > ::ParameterVectorType > | |
►Cshark::IParameterizable< CARTree< unsigned int > ::ParameterVectorType > | |
Cshark::AbstractModel< CARTree< unsigned int > ::InputType, RealVector, CARTree< unsigned int > ::ParameterVectorType > | |
►Cshark::IParameterizable< ModelType::ParameterVectorType > | |
Cshark::AbstractModel< ModelType::InputType, RealVector, ModelType::ParameterVectorType > | |
►Cshark::IParameterizable< ParameterType > | |
Cshark::AbstractModel< InputTypeT, OutputTypeT, ParameterType > | Base class for all Models |
►Cshark::IParameterizable< RealVector > | |
Cshark::AbstractModel< detail::BaseNearestNeighbor< InputType, unsigned int > ::InputType, unsigned int > | |
Cshark::AbstractModel< InputT, OutputT > | |
Cshark::AbstractModel< InputT, RealVector > | |
Cshark::AbstractModel< InputT, unsigned int > | |
Cshark::AbstractModel< InputType, RealVector > | |
Cshark::AbstractModel< KernelExpansion< InputType > ::InputType, unsigned int > | |
Cshark::AbstractModel< LinearModel< VectorType > ::InputType, unsigned int > | |
Cshark::AbstractModel< MeanModel< CARTree< unsigned int > > ::InputType, unsigned int > | |
Cshark::AbstractModel< Model::InputType, unsigned int > | |
Cshark::AbstractModel< RealVector, LabelType > | |
Cshark::AbstractModel< RealVector, RealVector > | |
Cshark::AbstractModel< RealVector, unsigned int > | |
Cshark::AbstractModel< VectorType, VectorType > | |
Cshark::RFTrainer< RealVector > | |
Cshark::RFTrainer< unsigned int > | |
►Cshark::IParameterizable<> | |
Cshark::AbstractClustering< RealVector > | |
Cshark::AbstractMetric< Batch< InputType >::type > | |
Cshark::AbstractMetric< InputType > | |
Cshark::AbstractMetric< MultiTaskSample< InputTypeT > > | |
Cshark::AbstractMetric< std::size_t > | |
Cshark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int, KernelClassifier< InputType >, AbstractWeightedTrainer< KernelClassifier< InputType > > > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int, KernelExpansion< InputType > > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int, MissingFeaturesKernelExpansion< InputType > > | |
Cshark::AbstractClustering< InputT > | Base class for clustering |
Cshark::AbstractLinearSvmTrainer< InputType > | Super class of all linear SVM trainers |
Cshark::AbstractMetric< InputTypeT > | |
Cshark::AbstractSvmTrainer< InputType, LabelType, Model, Trainer > | Super class of all kernelized (non-linear) SVM trainers |
Cshark::BinaryLayer | Layer of binary units taking values in {0,1} |
Cshark::BipolarLayer | Layer of bipolar units taking values in {-1,1} |
Cshark::GaussianLayer | A layer of Gaussian neurons |
Cshark::KernelBudgetedSGDTrainer< InputType, CacheType > | Budgeted stochastic gradient descent training for kernel-based models |
Cshark::KernelSGDTrainer< InputType, CacheType > | Generic stochastic gradient descent training for kernel-based models |
Cshark::LassoRegression< InputVectorType > | LASSO Regression |
Cshark::LDA | Linear Discriminant Analysis (LDA) |
Cshark::LinearRegression | Linear Regression |
Cshark::LinearSAGTrainer< InputType, LabelType > | Stochastic Average Gradient Method for training of linear models, |
Cshark::LogisticRegression< InputVectorType > | Trainer for Logistic regression |
Cshark::OneClassSvmTrainer< InputType, CacheType > | Training of one-class SVMs |
Cshark::TruncatedExponentialLayer | A layer of truncated exponential neurons |
►Cshark::ISerializable | Abstracts serializing functionality |
Cshark::AbstractClustering< RealVector > | |
Cshark::AbstractMetric< Batch< InputType >::type > | |
Cshark::AbstractMetric< InputType > | |
Cshark::AbstractMetric< MultiTaskSample< InputTypeT > > | |
Cshark::AbstractMetric< std::size_t > | |
Cshark::AbstractModel< CARTree< LabelType > ::InputType, RealVector, CARTree< LabelType > ::ParameterVectorType > | |
Cshark::AbstractModel< CARTree< unsigned int > ::InputType, RealVector, CARTree< unsigned int > ::ParameterVectorType > | |
Cshark::AbstractModel< detail::BaseNearestNeighbor< InputType, unsigned int > ::InputType, unsigned int > | |
Cshark::AbstractModel< InputT, OutputT > | |
Cshark::AbstractModel< InputT, RealVector > | |
Cshark::AbstractModel< InputT, unsigned int > | |
Cshark::AbstractModel< InputType, blas::vector< InputType::value_type, InputType::device_type >, blas::vector< InputType::value_type, InputType::device_type > > | |
Cshark::AbstractModel< InputType, RealVector > | |
Cshark::AbstractModel< InputType, unsigned int, VectorType > | |
Cshark::AbstractModel< KernelExpansion< InputType > ::InputType, unsigned int > | |
Cshark::AbstractModel< LinearModel< VectorType > ::InputType, unsigned int > | |
Cshark::AbstractModel< MeanModel< CARTree< unsigned int > > ::InputType, unsigned int > | |
Cshark::AbstractModel< Model::InputType, unsigned int > | |
Cshark::AbstractModel< ModelType::InputType, RealVector, ModelType::ParameterVectorType > | |
Cshark::AbstractModel< RealVector, LabelType > | |
Cshark::AbstractModel< RealVector, RealVector > | |
Cshark::AbstractModel< RealVector, unsigned int > | |
Cshark::AbstractModel< VectorType, blas::vector< VectorType ::value_type, VectorType ::device_type >, blas::vector< VectorType ::value_type, VectorType ::device_type > > | |
Cshark::AbstractModel< VectorType, VectorType > | |
Cshark::AbstractModel< VectorType, VectorType, VectorType > | |
Cshark::AbstractOptimizer< PointType, double, SingleObjectiveResultSet< PointType > > | |
Cshark::AbstractOptimizer< PointTypeT, RealVector, std::vector< ResultSet< PointTypeT, RealVector > > > | |
Cshark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > > | |
Cshark::AbstractOptimizer< RealVector, RealVector, std::vector< ResultSet< RealVector, RealVector > > > | |
Cshark::AbstractTrainer< KernelClassifier< InputType > > | |
Cshark::AbstractTrainer< KernelClassifier< InputType >, typename KernelClassifier< InputType > ::OutputType > | |
Cshark::AbstractTrainer< KernelClassifier< InputType >, unsigned int > | |
Cshark::AbstractTrainer< KernelExpansion< InputType >, RealVector > | |
Cshark::AbstractTrainer< KernelExpansion< InputType >, unsigned int > | |
Cshark::AbstractTrainer< LinearClassifier< InputType >, unsigned int > | |
Cshark::AbstractTrainer< LinearClassifier< InputVectorType >, typename LinearClassifier< InputVectorType > ::OutputType > | |
Cshark::AbstractTrainer< LinearClassifier<>, unsigned int > | |
Cshark::AbstractTrainer< LinearModel< InputVectorType > > | |
Cshark::AbstractTrainer< LinearModel<> > | |
Cshark::AbstractTrainer< LinearModel<>, unsigned int > | |
Cshark::AbstractTrainer< MissingFeaturesKernelExpansion< InputType >, unsigned int > | |
Cshark::AbstractTrainer< RFClassifier< RealVector >, typename RFClassifier< RealVector > ::OutputType > | |
Cshark::AbstractTrainer< RFClassifier< unsigned int >, typename RFClassifier< unsigned int > ::OutputType > | |
Cshark::AbstractUnsupervisedTrainer< KernelExpansion< InputType > > | |
Cshark::AbstractUnsupervisedTrainer< LinearModel< RealVector > > | |
Cshark::AbstractUnsupervisedTrainer< LinearModel<> > | |
Cshark::AbstractUnsupervisedTrainer< Normalizer< DataType > > | |
Cshark::AbstractUnsupervisedTrainer< ScaledKernel< InputType > > | |
►Cshark::detail::BaseWeightedDataset< LabeledData< InputT, LabelT > > | |
Cshark::WeightedLabeledData< InputT, LabelT > | Weighted data set for supervised learning |
►Cshark::detail::BaseWeightedDataset< UnlabeledData< DataT > > | |
Cshark::WeightedUnlabeledData< DataT > | Weighted data set for unsupervised learning |
►Cshark::Data< InputT > | |
Cshark::UnlabeledData< InputT > | Data set for unsupervised learning |
►Cshark::Data< InputType > | |
Cshark::UnlabeledData< InputType > | |
Cshark::Data< LabelT > | |
Cshark::Data< LabelType > | |
►Cshark::Data< RealVector > | |
Cshark::UnlabeledData< RealVector > | |
Cshark::Data< shark::MultiTaskSample > | |
Cshark::Data< unsigned int > | |
Cshark::LabeledData< InputType, LabelType > | |
Cshark::LabeledData< InputType, unsigned int > | |
Cshark::AbstractClustering< InputT > | Base class for clustering |
Cshark::AbstractMetric< InputTypeT > | |
Cshark::AbstractModel< InputTypeT, OutputTypeT, ParameterType > | Base class for all Models |
Cshark::AbstractOptimizer< PointType, ResultT, SolutionTypeT > | An optimizer that optimizes general objective functions |
Cshark::AbstractTrainer< Model, LabelTypeT > | Superclass of supervised learning algorithms |
Cshark::AbstractUnsupervisedTrainer< Model > | Superclass of unsupervised learning algorithms |
Cshark::BinaryLayer | Layer of binary units taking values in {0,1} |
Cshark::BipolarLayer | Layer of bipolar units taking values in {-1,1} |
Cshark::CSvmDerivative< InputType, CacheType > | This class provides two main member functions for computing the derivative of a C-SVM hypothesis w.r.t. its hyperparameters. The constructor takes a pointer to a KernelClassifier and an SvmTrainer, in the assumption that the former was trained by the latter. It heavily accesses their members to calculate the derivative of the alpha and offset values w.r.t. the SVM hyperparameters, that is, the regularization parameter C and the kernel parameters. This is done in the member function prepareCSvmParameterDerivative called by the constructor. After this initial, heavier computation step, modelCSvmParameterDerivative can be called on an input sample to the SVM model, and the method will yield the derivative of the hypothesis w.r.t. the SVM hyperparameters |
Cshark::Data< Type > | Data container |
Cshark::GaussianLayer | A layer of Gaussian neurons |
Cshark::LabeledData< InputT, LabelT > | Data set for supervised learning |
Cshark::LineSearch | Wrapper for the linesearch class of functions in the linear algebra library |
Cshark::MultiTaskSample< InputTypeT > | Aggregation of input data and task index |
Cshark::TruncatedExponentialLayer | A layer of truncated exponential neurons |
Cshark::TypedFlags< Flag > | Flexible and extensible mechanisms for holding flags |
Cshark::TypedFlags< Feature > | |
Cshark::IterativeNNQuery< DataContainer > | Iterative nearest neighbors query |
Cshark::JaakkolaHeuristic | Jaakkola's heuristic and related quantities for Gaussian kernel selection |
Cshark::KernelMatrix< InputType, CacheType > | Kernel Gram matrix |
Cshark::KeyValuePair< Key, Value > | Represents a Key-Value-Pair similar std::pair which is strictly ordered by it's key |
Cshark::LabeledDataDistribution< InputType, LabelType > | A LabeledDataDistribution defines a supervised learning problem |
Cshark::LabeledDataDistribution< InputType, unsigned int > | |
►Cshark::LabeledDataDistribution< RealVector, RealVector > | |
Cshark::Wave | Noisy sinc function: y = sin(x) / x + noise |
►Cshark::LabeledDataDistribution< RealVector, unsigned int > | |
Cshark::Chessboard | "chess board" problem for binary classification |
Cshark::CircleInSquare | |
Cshark::DiagonalWithCircle | |
Cshark::PamiToy | |
Cshark::LibSVMSelectionCriterion | Computes the maximum gian solution |
Cshark::LinearNeuron | Linear activation Neuron |
Cshark::LinearRankingSelection< Ordering > | Implements a fitness-proportional selection scheme for mating selection that scales the fitness values linearly before carrying out the actual selection |
Cshark::LogisticNeuron | Neuron which computes the Logistic (logistic) function with range [0,1] |
Cshark::LRUCache< T > | Implements an LRU-Caching Strategy for arbitrary Cache-Lines |
Cshark::LRUCache< QpFloatType > | |
Cshark::MarkovChain< Operator > | A single Markov chain |
Cshark::MaximumGainCriterion | Working set selection by maximization of the dual objective gain |
Cshark::MaximumGradientCriterion | Working set selection by maximization of the projected gradient |
Cshark::McPegasos< VectorType > | Pegasos solver for linear multi-class support vector machines |
►CMklKernelBase | |
Cshark::MklKernel< InputType > | Weighted sum of kernel functions |
Cshark::MultiTaskKernel< InputTypeT > | Special kernel function for multi-task and transfer learning |
Cshark::MNIST | Reads in the famous MNIST data in possibly binarized form. The MNIST database itself is not included in Shark, this class just helps loading it |
Cshark::ModifiedKernelMatrix< InputType, CacheType > | Modified Kernel Gram matrix |
Cshark::MultiNomialDistribution | Implements a multinomial distribution |
Cshark::MultiVariateNormalDistribution | Implements a multi-variate normal distribution with zero mean |
Cshark::MultiVariateNormalDistributionCholesky | Multivariate normal distribution with zero mean using a cholesky decomposition |
Cshark::MVPSelectionCriterion | Computes the most violating pair of the problem |
Cshark::CARTree< LabelType >::Node | |
►Cnoncopyable | |
Cshark::ScopedHandle< T > | |
Cshark::NormalizerNeuron< VectorType > | |
Cshark::NSGA3Indicator | |
Cshark::OnePointCrossover | Implements one-point crossover |
Cshark::PartiallyMappedCrossover | Implements partially mapped crossover |
Cshark::PartlyPrecomputedMatrix< Matrix > | Partly Precomputed version of a matrix for quadratic programming |
Cshark::Pegasos< VectorType > | Pegasos solver for linear (binary) support vector machines |
Cshark::PenalizingEvaluator | Penalizing evaluator for scalar objective functions |
Cshark::HypervolumeContributionApproximator::Point< VectorType > | Models a point and associated information for book-keeping purposes |
Cshark::EvaluationArchive< PointType, ResultT >::PointResultPairType | Pair of point and result |
Cshark::PolynomialMutator | Polynomial mutation operator |
Cshark::PopulationBasedStepSizeAdaptation | Step size adaptation based on the success of the new population compared to the old |
Cshark::PrecomputedMatrix< Matrix > | Precomputed version of a matrix for quadratic programming |
Cshark::QpMcSimplexDecomp< Matrix >::PreferedSelectionStrategy | Working set selection eturning th S2DO working set |
Cshark::QpMcBoxDecomp< Matrix >::PreferedSelectionStrategy | Working set selection eturning th S2DO working set |
Cshark::QpBoxLinear< InputT > | Quadratic program solver for box-constrained problems with linear kernel |
►Cshark::QpConfig | Super class of all support vector machine trainers |
Cshark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int, KernelClassifier< InputType >, AbstractWeightedTrainer< KernelClassifier< InputType > > > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int, KernelExpansion< InputType > > | |
Cshark::AbstractSvmTrainer< InputType, unsigned int, MissingFeaturesKernelExpansion< InputType > > | |
Cshark::AbstractLinearSvmTrainer< InputType > | Super class of all linear SVM trainers |
Cshark::AbstractSvmTrainer< InputType, LabelType, Model, Trainer > | Super class of all kernelized (non-linear) SVM trainers |
Cshark::OneClassSvmTrainer< InputType, CacheType > | Training of one-class SVMs |
Cshark::QpMcBoxDecomp< Matrix > | |
►Cshark::QpMcLinear< InputT > | Generic solver skeleton for linear multi-class SVM problems |
Cshark::QpMcLinearADM< InputT > | Solver for the multi-class SVM with absolute margin and discriminative maximum loss |
Cshark::QpMcLinearATM< InputT > | Solver for the multi-class SVM with absolute margin and total maximum loss |
Cshark::QpMcLinearATS< InputT > | Solver for the multi-class SVM with absolute margin and total sum loss |
Cshark::QpMcLinearCS< InputT > | Solver for the multi-class SVM by Crammer & Singer |
Cshark::QpMcLinearLLW< InputT > | Solver for the multi-class SVM by Lee, Lin & Wahba |
Cshark::QpMcLinearMMR< InputT > | Solver for the multi-class maximum margin regression SVM |
Cshark::QpMcLinearReinforced< InputT > | Solver for the "reinforced" multi-class SVM |
Cshark::QpMcLinearWW< InputT > | Solver for the multi-class SVM by Weston & Watkins |
Cshark::QpMcSimplexDecomp< Matrix > | |
Cshark::QpSolutionProperties | Properties of the solution of a quadratic program |
Cshark::QpSolver< Problem, SelectionStrategy > | Quadratic program solver |
Cshark::QpSparseArray< QpFloatType > | Specialized container class for multi-class SVM problems |
Cshark::QpStoppingCondition | Stopping conditions for quadratic programming |
Cshark::Individual< PointType, FitnessTypeT, Chromosome >::RankOrdering | Ordering relation by the ranks of the individuals |
Cshark::RealSpace | The RealSpace can't be enumerated. Infinite values are just too much |
Cshark::tags::RealSpace | A Tag for EnumerationSpaces. It tells the Functions, that the space is real and can't be enumerated |
Cshark::RectifierNeuron | Rectifier Neuron f(x) = max(0,x) |
Cshark::ReferenceVectorAdaptation< IndividualType > | Reference vector adaptation for the RVEA algorithm |
Cshark::ReferenceVectorAdaptation< shark::Individual > | |
Cshark::ReferenceVectorGuidedSelection< IndividualType > | Implements the reference vector selection for the RVEA algorithm |
Cshark::ReferenceVectorGuidedSelection< shark::Individual > | |
Cshark::RegularizedKernelMatrix< InputType, CacheType > | Kernel Gram matrix with modified diagonal |
Cshark::RadiusMarginQuotient< InputType, CacheType >::Result | |
Cshark::ResultSet< SearchPointT, ResultT > | |
►Cshark::ResultSet< SearchPointTypeT, double > | |
►Cshark::SingleObjectiveResultSet< SearchPointTypeT > | Result set for single objective algorithm |
Cshark::ValidatedSingleObjectiveResultSet< SearchPointTypeT > | Result set for validated points |
Cshark::statistics::ResultTable< Parameter > | Stores results of a running experiment |
Cshark::RFTrainer< LabelType > | Random Forest |
Cshark::ROC | ROC-Curve - false negatives over false positives |
Cshark::RouletteWheelSelection | Fitness-proportional selection operator |
Cshark::QpSparseArray< QpFloatType >::Row | Data structure describing a row of the sparse array |
Cshark::AbstractObjectiveFunction< PointType, ResultT >::SecondOrderDerivative | |
Cshark::Shape | Represents the Shape of an input or output |
Cshark::Shark | Allows for querying compile settings at runtime. Provides the current command line arguments to the rest of the library |
►CSHARK_ITERATOR_FACADE | |
Cshark::IndexedIterator< Iterator > | Creates an Indexed Iterator, an Iterator which also carries index information using index() |
Cshark::IndexingIterator< Container > | |
Cshark::ProxyIterator< Sequence, ValueType, Reference > | Creates an iterator which reinterpretes an object as a range |
Cshark::Shifter | Shifter problem |
►Cshark::detail::SimpleBatch< WeightedDataBatch< detail::element_to_batch< DataType >::type, detail::element_to_batch< WeightType >::type > > | |
Cshark::Batch< WeightedDataPair< DataType, WeightType > > | |
Cshark::SimulatedBinaryCrossover< PointType > | Simulated binary crossover operator |
Cshark::SimulatedBinaryCrossover< RealVector > | |
Cshark::SimulatedBinaryCrossover< SearchPointType > | |
Cshark::SinglePole | |
Cshark::SoftmaxNeuron< VectorType > | |
►Cshark::State | Represents the State of an Object |
Cshark::EmptyState | Default State of an Object which does not need a State |
Cshark::NormalizerNeuron< VectorType >::State | |
Cshark::statistics::Statistics< Parameter > | Generates Statistics over the results of an experiment |
►Cshark::detail::SubrangeKernelBase< InputType > | |
Cshark::SubrangeKernel< InputType, InnerKernel > | Weighted sum of kernel functions |
►Cshark::SvmProblem< Problem > | |
►Cshark::BoxBasedShrinkingStrategy< SvmProblem< Problem > > | |
Cshark::SvmShrinkingProblem< Problem > | |
Cshark::TanhNeuron | Neuron which computes the hyperbolic tangenst with range [-1,1] |
Cshark::WeightedSumKernel< InputType >::tBase | Structure describing a single m_base kernel |
Cshark::TemperedMarkovChain< Operator > | |
Cshark::Timer | Timer abstraction with microsecond resolution |
Cshark::TournamentSelection< Predicate > | Tournament selection operator |
Cboost::serialization::tracking_level< shark::TypedFlags< T > > | |
Cboost::serialization::tracking_level< std::vector< T > > | |
Cshark::TransformedData< Functor, T > | |
Cshark::TreeConstruction | Stopping criteria for tree construction |
Cshark::TwoPointStepSizeAdaptation | Step size adaptation based on the success of the new population compared to the old |
Cshark::TwoStateSpace< State1, State2 > | The TwoStateSpace is a discrete Space with only two values, for example {0,1} or {-1,1} |
►Ctype | |
Cshark::Batch< detail::MarkovChainSample< HiddenSample, VisibleSample > > | |
►Cshark::Batch< detail::MatrixRowReference< M >::Vector > | |
Cshark::Batch< detail::MatrixRowReference< M > > | |
Cshark::Batch< T > | Class which helps using different batch types |
Cshark::UniformCrossover | Uniform crossover of arbitrary individuals |
Cshark::UniformRankingSelection | Selects individuals from the range of individual and offspring individuals |
Cshark::QpMcSimplexDecomp< Matrix >::Variable | Data structure describing one variable of the problem |
Cshark::QpMcBoxDecomp< Matrix >::Variable | Data structure describing one m_variables of the problem |
►Cshark::detail::VectorBatch< blas::matrix< T > > | |
Cshark::Batch< blas::vector< T > > | Specialization for vectors which should be matrices in batch mode! |
Cshark::Shark::Version< major, minor, patch > | Models a version according to the major.minor.patch versioning scheme |
Cshark::WeightedDataBatch< DataBatchType, WeightBatchType > | |
Cshark::WeightedDataPair< DataType, WeightType > | Input-Label pair of data |
Cshark::WS2MaximumGradientCriterion | Working set selection by maximization of the projected gradient |
►CProblem | |
Cshark::BoxBasedShrinkingStrategy< Problem > | Takes q boxx constrained QP-type problem and implements shrinking on it |
►CTrainer | |
Cshark::AbstractSvmTrainer< InputType, LabelType, Model, Trainer > | Super class of all kernelized (non-linear) SVM trainers |