Uses of Interface
jsat.parameters.Parameterized

Packages that use Parameterized

Package	Description
jsat.classifiers
jsat.classifiers.bayesian
jsat.classifiers.boosting
jsat.classifiers.calibration
jsat.classifiers.knn
jsat.classifiers.linear
jsat.classifiers.linear.kernelized
jsat.classifiers.neuralnetwork
jsat.classifiers.svm
jsat.classifiers.svm.extended
jsat.classifiers.trees
jsat.clustering
jsat.clustering.kmeans
jsat.datatransform
jsat.datatransform.kernel
jsat.distributions.kernels
jsat.distributions.multivariate
jsat.math.decayrates
jsat.regression
jsat.text.topicmodel

Uses of Parameterized in jsat.classifiers

Classes in jsat.classifiers that implement Parameterized

Modifier and Type	Class and Description
class	DDAG Decision Directed Acyclic Graph (DDAG) classifier.
class	OneVSAll This classifier turns any classifier, specifically binary classifiers, into multi-class classifiers.
class	OneVSOne A One VS One classifier extends binary decision classifiers into multi-class decision classifiers.
class	RegressorToClassifier This meta algorithm wraps a Regressor to perform binary classification.

Uses of Parameterized in jsat.classifiers.bayesian

Classes in jsat.classifiers.bayesian that implement Parameterized

Modifier and Type	Class and Description
class	BestClassDistribution BestClassDistribution is a generic class for performing classification by fitting a MultivariateDistribution to each class.
class	MultinomialNaiveBayes An implementation of the Multinomial Naive Bayes model (MNB).
class	MultivariateNormals This classifier can be seen as an extension of NaiveBayes.
class	NaiveBayes Provides an implementation of the Naive Bayes classifier that assumes numeric features come from some continuous probability distribution.

Uses of Parameterized in jsat.classifiers.boosting

Classes in jsat.classifiers.boosting that implement Parameterized

Modifier and Type	Class and Description
class	AdaBoostM1 Implementation of Experiments with a New Boosting Algorithm, by Yoav Freund&Robert E.
class	AdaBoostM1PL An extension to the original AdaBoostM1 algorithm for parallel training.
class	ArcX4 Arc-x4 is a ensemble-classifier that performs re-weighting of the data points based on the total number of errors that have occurred for the data point.
class	Bagging An implementation of Bootstrap Aggregating, as described by LEO BREIMAN in "Bagging Predictors".
class	EmphasisBoost Emphasis Boost is a generalization of the Real AdaBoost algorithm, expanding the update term and providing the λ term to control the trade off.
class	LogitBoost An implementation of the original 2 class LogitBoost algorithm.
class	LogitBoostPL An extension to the original LogitBoost algorithm for parallel training.
class	ModestAdaBoost Modest Ada Boost is a generalization of Discrete Ada Boost that attempts to reduce the generalization error and avoid over-fitting.
class	SAMME This is an implementation of the Multi-Class AdaBoost method SAMME (Stagewise Additive Modeling using a Multi-Class Exponential loss function), presented in Multi-class AdaBoost by Ji Zhu, Saharon Rosset, Hui Zou,&Trevor Hasstie This algorithm reduces to AdaBoostM1 for binary classification problems.
class	Wagging Wagging is a meta-classifier that is related to Bagging.
class	WaggingNormal Wagging using the Normal distribution.

Uses of Parameterized in jsat.classifiers.calibration

Classes in jsat.classifiers.calibration that implement Parameterized

Modifier and Type	Class and Description
class	BinaryCalibration This abstract class provides the frame work for an algorithm to perform probability calibration based on the outputs of a base learning algorithm for binary classification problems.
class	IsotonicCalibration Isotonic Calibration is non-parametric, and only assumes that the underlying distribution from negative to positive examples is strictly a non-decreasing function.
class	PlattCalibration Platt Calibration essentially performs logistic regression on the output scores of a model against their class labels.

Uses of Parameterized in jsat.classifiers.knn

Classes in jsat.classifiers.knn that implement Parameterized

Modifier and Type	Class and Description
class	DANN DANN is an implementation of Discriminant Adaptive Nearest Neighbor.
class	LWL Locally Weighted Learner (LW) is the combined generalized implementation of Locally Weighted Regression (LWR) and Locally Weighted Naive Bayes (LWNB).
class	NearestNeighbour An implementation of the Nearest Neighbor algorithm, but with a British spelling! How fancy.

Uses of Parameterized in jsat.classifiers.linear

Classes in jsat.classifiers.linear that implement Parameterized

Modifier and Type	Class and Description
class	AROW An implementation of Adaptive Regularization of Weight Vectors (AROW), which uses second order information to learn a large margin binary classifier.
class	BBR This is an implementation of Bayesian Binary Regression for L1 and L2 regularized logistic regression.
class	LinearBatch LinearBatch learns either a classification or regression problem depending on the loss function ℓ(w,x) used.
class	LinearL1SCD Implements an iterative and single threaded form of fast Stochastic Coordinate Decent for optimizing L1 regularized linear regression problems.
class	LinearSGD LinearSGD learns either a classification or regression problem depending on the loss function ℓ(w,x) used.
class	LogisticRegressionDCD This provides an implementation of regularized logistic regression using Dual Coordinate Descent.
class	NewGLMNET NewGLMNET is a batch method for solving Elastic Net regularized Logistic Regression problems of the form 0.5 * (1-α) ||w||2 + α * ||w||1 + C * ∑Ni=1 ℓ (wT xi + b, yi).
class	NHERD Implementation of the Normal Herd (NHERD) algorithm for learning a linear binary classifier.
class	PassiveAggressive An implementations of the 3 versions of the Passive Aggressive algorithm for binary classification and regression.
class	SCD Implementation of Stochastic Coordinate Descent for L1 regularized classification and regression.
class	SCW Provides an Implementation of Confidence-Weighted (CW) learning and Soft Confidence-Weighted (SCW), both of which are binary linear classifiers inspired by PassiveAggressive.
class	SMIDAS Implements the iterative and single threaded stochastic solver for L1 regularized linear regression problems SMIDAS (Stochastic Mirror Descent Algorithm mAde Sparse).
class	SPA Support class Passive Aggressive (SPA) is a multi class generalization of PassiveAggressive.
class	STGD This provides an implementation of Sparse Truncated Gradient Descent for L1 regularized linear classification and regression on sparse data sets.
class	StochasticMultinomialLogisticRegression This is a Stochastic implementation of Multinomial Logistic Regression.
class	StochasticSTLinearL1 This base class provides shared functionality and variables used by two different training algorithms for L1 regularized linear models.

Uses of Parameterized in jsat.classifiers.linear.kernelized

Classes in jsat.classifiers.linear.kernelized that implement Parameterized

Modifier and Type	Class and Description
class	ALMA2K Provides a kernelized version of the ALMA2 algorithm.
class	BOGD Bounded Online Gradient Descent (BOGD) is a kernel learning algorithm that uses a bounded number of support vectors.
class	CSKLR An implementation of Conservative Stochastic Kernel Logistic Regression.
class	CSKLRBatch An implementation of Conservative Stochastic Kernel Logistic Regression.
class	DUOL Provides an implementation of Double Update Online Learning (DUOL) algorithm.
class	Forgetron Implementation of the first two Forgetron algorithms.
class	KernelSGD Kernel SGD is the kernelized counterpart to LinearSGD, and learns nonlinear functions via the kernel trick.
class	OSKL Online Sparse Kernel Learning by Sampling and Smooth Losses (OSKL) is an online algorithm for learning sparse kernelized solutions to binary classification problems.
class	Projectron An implementation of the Projectron and Projectrion++ algorithms.

Uses of Parameterized in jsat.classifiers.neuralnetwork

Classes in jsat.classifiers.neuralnetwork that implement Parameterized

Modifier and Type	Class and Description
class	BackPropagationNet An implementation of a Feed Forward Neural Network (NN) trained by Back Propagation.
class	DReDNetSimple This class provides a neural network based on Geoffrey Hinton's Deep Rectified Dropout Nets.
class	LVQ Learning Vector Quantization (LVQ) is an algorithm that extends SOM to take advantage of label information to perform classification.
class	LVQLLC LVQ with Locally Learned Classifier (LVQ-LLC) is an adaption of the LVQ algorithm I have come up with.
class	RBFNet This provides a highly configurable implementation of a Radial Basis Function Neural Network.
class	SOM An implementation of a Self Organizing Map, also called a Kohonen Map.

Uses of Parameterized in jsat.classifiers.svm

Classes in jsat.classifiers.svm that implement Parameterized

Modifier and Type	Class and Description
class	DCD Implements Dual Coordinate Descent (DCD) training algorithms for a Linear L1 or L2 Support Vector Machine for binary classification and regression.
class	DCDs Implements Dual Coordinate Descent with shrinking (DCDs) training algorithms for a Linear L1 or L2 Support Vector Machine for binary classification and regression.
class	DCSVM This is an implementation of the Divide-and-Conquer Support Vector Machine (DC-SVM).
class	LSSVM The Least Squares Support Vector Machine (LS-SVM) is an alternative to the standard SVM classifier for regression and binary classification problems.
class	Pegasos Implements the linear kernel mini-batch version of the Pegasos SVM classifier.
class	PegasosK Implements the kernelized version of the Pegasos algorithm for SVMs.
class	PlattSMO An implementation of SVMs using Platt's Sequential Minimum Optimization (SMO) for both Classification and Regression problems.
class	SBP Implementation of the Stochastic Batch Perceptron (SBP) algorithm.

Uses of Parameterized in jsat.classifiers.svm.extended

Classes in jsat.classifiers.svm.extended that implement Parameterized

Modifier and Type	Class and Description
class	AMM This is the batch variant of the Adaptive Multi-Hyperplane Machine (AMM) algorithm.
class	CPM This class implements the Convex Polytope Machine (CPM), which is an extension of the Linear SVM.
class	OnlineAMM This is the Online variant of the Adaptive Multi-Hyperplane Machine (AMM) algorithm.

Uses of Parameterized in jsat.classifiers.trees

Classes in jsat.classifiers.trees that implement Parameterized

Modifier and Type	Class and Description
class	DecisionStump This class is a 1-rule.
class	DecisionTree Creates a decision tree from DecisionStumps.
class	ERTrees Extra Randomized Trees (ERTrees) is an ensemble method built on top of ExtraTree.
class	ExtraTree The ExtraTree is an Extremely Randomized Tree.
class	RandomDecisionTree An extension of Decision Trees, it ignores the given set of features to use- and selects a new random subset of features at each node for use.
class	RandomForest Random Forest is an extension of Bagging that is applied only to DecisionTrees.

Uses of Parameterized in jsat.clustering

Classes in jsat.clustering that implement Parameterized

Modifier and Type	Class and Description
class	FLAME Provides an implementation of the FLAME clustering algorithm.
class	GapStatistic This class implements a method for estimating the number of clusters in a data set called the Gap Statistic.
class	HDBSCAN HDBSCAN is a density based clustering algorithm that is an improvement over DBSCAN.
class	LSDBC A parallel implementation of Locally Scaled Density Based Clustering.
class	OPTICS An Implementation of the OPTICS algorithm, which is a generalization of DBSCAN.

Uses of Parameterized in jsat.clustering.kmeans

Classes in jsat.clustering.kmeans that implement Parameterized

Modifier and Type	Class and Description
class	ElkanKernelKMeans An efficient implementation of the K-Means algorithm.
class	ElkanKMeans An efficient implementation of the K-Means algorithm.
class	GMeans This class provides a method of performing KMeans clustering when the value of K is not known.
class	HamerlyKMeans An efficient implementation of the K-Means algorithm.
class	KernelKMeans Base class for various Kernel K Means implementations.
class	KMeans Base class for the numerous implementations of k-means that exist.
class	KMeansPDN This class provides a method of performing KMeans clustering when the value of K is not known.
class	LloydKernelKMeans An implementation of the naive algorithm for performing kernel k-means.
class	NaiveKMeans An implementation of Lloyd's K-Means clustering algorithm using the naive algorithm.
class	XMeans This class provides a method of performing KMeans clustering when the value of K is not known.

Uses of Parameterized in jsat.datatransform

Classes in jsat.datatransform that implement Parameterized

Modifier and Type	Class and Description
class	DataModelPipeline A Data Model Pipeline combines several data transforms and a base Classifier or Regressor into a unified object for performing classification and Regression with.
class	DataTransformBase This abstract class implements the Parameterized interface to ease the development of simple Data Transforms.
class	DataTransformProcess Performing a transform on the whole data set before training a classifier can add bias to the results.
class	JLTransform The Johnson-Lindenstrauss (JL) Transform is a type of random projection down to a lower dimensional space.
class	WhitenedPCA An extension of PCA that attempts to capture the variance, and make the variables in the output space independent from each-other.
class	WhitenedZCA An extension of WhitenedPCA, is the Whitened Zero Component Analysis.

Uses of Parameterized in jsat.datatransform.kernel

Classes in jsat.datatransform.kernel that implement Parameterized

Modifier and Type	Class and Description
class	KernelPCA A kernelized implementation of PCA.
class	Nystrom An implementation of the Nystrom approximation for any Kernel Trick.
class	RFF_RBF An Implementation of Random Fourier Features for the RBFKernel.

Uses of Parameterized in jsat.distributions.kernels

Subinterfaces of Parameterized in jsat.distributions.kernels

Modifier and Type	Interface and Description
interface	KernelTrick The KernelTrick is a method can can be used to alter an algorithm to do its calculations in a projected feature space, without explicitly forming the features.

Classes in jsat.distributions.kernels that implement Parameterized

Modifier and Type	Class and Description
class	BaseKernelTrick This provides a simple base implementation for the cache related methods in Kernel Trick.
class	BaseL2Kernel Many Kernels can be described in terms the L2 norm with some operations performed on it.
class	DistanceMetricBasedKernel This abstract class provides the means of implementing a Kernel based off some DistanceMetric.
class	GeneralRBFKernel This class provides a generalization of the RBFKernel to arbitrary distance metrics, and is of the form exp(-d(x, y)2/(2 σ2 )).
class	LinearKernel Provides a linear kernel function, which computes the normal dot product.
class	NormalizedKernel This provides a wrapper kernel that produces a normalized kernel trick from any input kernel trick.
class	PolynomialKernel Provides a Polynomial Kernel of the form k(x,y) = (alpha * x.y + c)^d
class	PukKernel The PUK kernel is an alternative to the RBF Kernel.
class	RationalQuadraticKernel Provides an implementation of the Rational Quadratic Kernel, which is of the form: k(x, y) = 1 - ||x-y||2 / (||x-y||2 + c)
class	RBFKernel Provides a kernel for the Radial Basis Function, which is of the form k(x, y) = exp(-||x-y||2/(2*σ2))
class	SigmoidKernel Provides an implementation of the Sigmoid (Hyperbolic Tangent) Kernel, which is of the form: k(x, y) = tanh(alpha * < x, y > +c) Technically, this kernel is not positive definite.

Uses of Parameterized in jsat.distributions.multivariate

Classes in jsat.distributions.multivariate that implement Parameterized

Modifier and Type	Class and Description
class	MetricKDE MetricKDE is a generalization of the KernelDensityEstimator to the multivariate case.

Uses of Parameterized in jsat.math.decayrates

Classes in jsat.math.decayrates that implement Parameterized

Modifier and Type	Class and Description
class	ExponetialDecay The Exponential Decay requires the maximum time step to be explicitly known ahead of time.
class	InverseDecay Decays an input by the inverse of the amount of time that has occurred, the max time being irrelevant.
class	LinearDecay The Linear Decay requires the maximum time step to be explicitly known ahead of time.
class	PowerDecay Decays an input by power of the amount of time that has occurred, the max time being irrelevant.

Uses of Parameterized in jsat.regression

Classes in jsat.regression that implement Parameterized

Modifier and Type	Class and Description
class	KernelRidgeRegression A kernelized implementation of Ridge Regression.
class	KernelRLS Provides an implementation of the Kernel Recursive Least Squares algorithm.
class	NadarayaWatson The Nadaraya-Watson regressor uses the Kernel Density Estimator to perform regression on a data set.
class	OrdinaryKriging An implementation of Ordinary Kriging with support for a uniform error measurement.
class	RANSAC RANSAC is a randomized meta algorithm that is useful for fitting a model to a data set that has a large amount of outliers that do not represent the true distribution well.
class	RidgeRegression An implementation of Ridge Regression that finds the exact solution.
class	StochasticGradientBoosting An implementation of Stochastic Gradient Boosting (SGB) for the Squared Error loss.
class	StochasticRidgeRegression A Stochastic implementation of Ridge Regression.

Uses of Parameterized in jsat.text.topicmodel

Classes in jsat.text.topicmodel that implement Parameterized

Modifier and Type	Class and Description
class	OnlineLDAsvi This class provides an implementation of Latent Dirichlet Allocation for learning a topic model from a set of documents.