Models

Model classes for statistical prediction.

Models in shark define the classes that can perform statistical predictions on supplied input data. Models can have different types of inputs and outputs so that they can be sued for classification and regression tasks.

Collaboration diagram for Models:

Classes
class	shark::AbstractModel< InputTypeT, OutputTypeT, ParameterVectorType >
	Base class for all Models. More...
class	shark::Classifier< Model >
	Conversion of real-valued or vector valued outputs to class labels. More...
class	shark::CMACMap
	The CMACMap class represents a linear combination of piecewise constant functions. More...
class	shark::ConcatenatedModel< VectorType >
	ConcatenatedModel concatenates two models such that the output of the first model is input to the second. More...
class	shark::Conv2DModel< VectorType, ActivationFunction >
	Convolutional Model for 2D image data. More...
class	shark::DropoutLayer< VectorType >
	Implements Dropout layer semantics. More...
class	shark::Ensemble< ModelType, OutputType >
	Represents en weighted ensemble of models. More...
class	shark::KernelExpansion< InputType >
	Linear model in a kernel feature space. More...
struct	shark::KernelClassifier< InputType >
	Linear classifier in a kernel feature space. More...
class	shark::MissingFeaturesKernelExpansion< InputType >
	Kernel expansion with missing features support For a choice of kernel, see Kernels. More...
class	shark::LinearModel< InputType, ActivationFunction >
	Linear Prediction with optional activation function. More...
class	shark::LinearClassifier< VectorType >
	Basic linear classifier. More...
class	shark::NearestNeighborModel< InputType, LabelType >
	NearestNeighbor model for classification and regression. More...
class	shark::NeuronLayer< NeuronType, VectorType >
	Neuron activation layer. More...
class	shark::Normalizer< VectorType >
	"Diagonal" linear model for data normalization. More...
class	shark::OneVersusOneClassifier< InputType, VectorType >
	One-versus-one Classifier. More...
class	shark::PoolingLayer< VectorType >
	Performs Pooling operations for a given input image. More...
class	shark::RBFLayer
	Implements a layer of radial basis functions in a neural network. More...
class	shark::ResizeLayer< VectorType >
	Resizes an input image to a given size. More...
class	shark::CARTree< LabelType >
	Classification and Regression Tree. More...
class	shark::RFClassifier< LabelType >
	Random Forest Classifier. More...

Modules
	Clustering Algorithms
	Kernels
	Neuron activation functions
	Space Partitioning Trees