Accord.MachineLearning Namespace

Bag of words.

Bag of words.

Bag of words.

Codebook learning statistics for BagOfWords models.

Balanced K-Means algorithm. Note: The balanced clusters will be available in the Labels property of this instance!

Base class for Bag of Visual Words implementations.

Base class for Bag of Audiovisual Words implementations.

Utility class for preparing mini-batches of data.

Base class for K-Nearest Neighbor (k-NN) algorithms.

Utility class for preparing mini-batches of data.

Base class for binary classifiers.

Common base class for supervised learning algorithms for binary classifiers.

Base class for generative binary classifiers.

Base class for score-based binary classifiers.

Binary split clustering algorithm.

Boltzmann distribution exploration policy.

Obsolete. Please use BootstrapTModel, TInput, TOutput instead.

Obsolete. Please refer to BootstrapTModel, TInput, TOutput instead.

Obsolete. Please refer to BootstrapTModel, TInput, TOutput instead.

Data cluster.

Data cluster.

Base class for multi-class and multi-label classifiers.

Base class for a data cluster.

k-Fold cross-validation. Please only use the static methods contained in this class, the rest are marked as obsolete.

Obsolete. Please use CrossValidationTModel, TInput, TOutput instead.

Obsolete. Please refer to CrossValidationTModel, TInput instead.

Summary statistics for a cross-validation trial.

Obsolete. Please refer to CrossValidationTModel, TInput instead.

Obsolete. Please refer to CrossValidationTModel, TInput instead.

Early stopping training procedure.

Epsilon greedy exploration policy.

Gaussian Mixture Model Cluster Collection.

Gaussian Mixture Model cluster.

Gaussian mixture model clustering.

Options for Gaussian Mixture Model fitting.

Grid search procedure for automatic parameter tuning.

Grid search parameter collection.

Range of parameters to be tested in a grid search.

GridSearchRange collection.

Contains results from the grid-search procedure.

Parameters for learning a binary decision model. An object of this class is passed by OneVsRestLearningTBinary, TModel or OneVsOneLearningTBinary, TModel to instruct how binary learning algorithms should create their binary classifiers.

Lloyd's k-Means clustering algorithm.

k-Means cluster collection.

k-Means' cluster.

k-Medoids clustering using PAM (Partition Around Medoids) algorithm.

k-Medoids clustering using PAM (Partition Around Medoids) algorithm.

k-Medoids cluster collection.

k-Medoids' cluster.

k-Modes algorithm.

k-Modes algorithm.

k-Modes cluster collection.

k-Modes' cluster.

K-Nearest Neighbor (k-NN) algorithm.

K-Nearest Neighbor (k-NN) algorithm.

Base implementation for generative observation sequence taggers. A sequence tagger can predict the class label of each individual observation in a input sequence vector.

Mean shift clustering algorithm.

Mean shift cluster collection.

Mean shift cluster.

Utility class for preparing mini-batches of data.

Utility class for preparing mini-batches of data.

Fast k-means clustering algorithm.

Minimum (Mean) Distance Classifier.

Base class for multi-class classifiers.

Base class for multi-class classifiers.

Base class for multi-class learning algorithm.

Base class for multi-class learning algorithm.

Base class for generative multi-class classifiers.

Base class for score-based multi-class classifiers.

Base class for multi-label classifiers.

Base class for generative multi-label classifiers.

Base class for score-based multi-label classifiers.

Base class for data transformation algorithms.

One-Vs-One construction for solving multi-class classification using a set of binary classifiers.

One-Vs-One construction for solving multi-class classification using a set of binary classifiers.

Base learning algorithm for OneVsOneTBinary, TInput multi-class classifiers.

Base learning algorithm for OneVsOneTBinary, TInput multi-class classifiers.

Base class for multi-class classifiers based on the "one-vs-rest" construction based on binary classifiers.

Base class for multi-class classifiers based on the "one-vs-rest" construction based on binary classifiers.

Base learning algorithm for OneVsRestTModel, TInput multi-class classifiers.

Base learning algorithm for OneVsRestTModel, TInput multi-class classifiers.

Base class for parallel learning algorithms.

QLearning learning algorithm.

Multipurpose RANSAC algorithm.

Roulette wheel exploration policy.

Sarsa learning algorithm.

Common base class for observation sequence taggers.

Obsolete. Please refer to SplitSetValidationTModel, TInput instead.

Obsolete. Please refer to SplitSetValidationTModel, TInput, TOutput instead.

Summary statistics for a Split-set validation trial.

Obsolete. Please refer to SplitSetValidationTModel, TInput, TOutput instead.

Obsolete. Please use SplitSetValidationTModel, TInput, TOutput instead.

Subproblem progress event argument.

Tabu search exploration policy.

Base class for multi-class and multi-label classifiers.

Term Frequency - Inverse Term Frequency.

Set of machine learning tools.

Base class for data transformation algorithms.

Base class for data transformation algorithms.

Base class for data transformation algorithms.

k-Medoids clustering using Voronoi iteration algorithm.

k-Medoids clustering using Voronoi iteration algorithm.

Pair of class labels.

Decision between two class labels. Indicates the class index of the first class, the class index of the adversary, and the class index of the winner.

Contains the name and value of a parameter that should be used during fitting.

Common interface for Bag of Words objects.

Common interface for classification models. Classification models learn how to produce a class-label (or a set of class labels) y from an input vector x.

Common interface for classification models. Classification models learn how to produce a class-label (or a set of class labels) y from an input vector x.

Common interface for generative binary classifiers. A binary classifier can predict whether or not an instance belongs to a class, while at the same time being able to provide the probability of this sample belonging to the positive class.

Common interface for score-based binary classifiers. A binary classifier can predict whether or not an instance belongs to a class based on a decision score (a real number) that measures the association of the input with the negative and positive class.

Common interface for clusters that contains centroids which are of the same data type as the clustered data types (i.e. KMeansClusterCollectionKMeansCluster).

Common interface for clusters that contains centroids, where the centroid data type might be different from the data type of the data bring clustered (i.e. GaussianClusterCollectionGaussianCluster).

Common interface for classification models. Classification models learn how to produce a class-label (or a set of class labels) y from an input vector x.

Common interface for classification models. Classification models learn how to produce a class-label (or a set of class labels) y from an input vector x.

Common interface for cluster collections.

Common interface for cluster collections.

Common interface for collections of clusters (i.e. KMeansClusterCollection, GaussianClusterCollection, MeanShiftClusterCollection).

Common interface for clustering algorithms.

Common interface for clustering algorithms.

Common interface for data transformation algorithms. Examples of transformations include classifiers, regressions and other machine learning techniques.

Common interface for unsupervised learning algorithms.

Exploration policy interface.

Common interface for generative models.

Common interface for generative observation sequence taggers. A sequence tagger can predict the class label of each individual observation in a input sequence vector.

Common interface for multi-class models. Classification models learn how to produce a class-label y from an input vector x.

Common interface for multi-class models. Classification models learn how to produce a class-label y from an input vector x.

Common interface for multi-class models. Classification models learn how to produce a class-label y from an input vector x.

Common interface for generative multi-class classifiers. A multi-class classifier can predicts a class label based on an input instance vector.

Common interface for generative multi-class classifiers. A multi-class classifier can predicts a class label based on an input instance vector.

Common interface for generative multi-class classifiers. A multi-class classifier can predicts a class label based on an input instance vector.

Common interface for generative multi-class classifiers. A multi-class classifier can predicts a class label based on an input instance vector.

Common interface for score-based multi-class classifiers. A multi-class classifier can predict to which class an instance belongs based on a decision score (a real number) that measures the association of the input with each class.

Common interface for generative multi-class classifiers. A multi-class classifier can predicts a class label based on an input instance vector.

Common interface for score-based multi-class classifiers. A multi-class classifier can predict to which class an instance belongs based on a decision score (a real number) that measures the association of the input with each class.

Common interface for score-based multi-class classifiers. A multi-class classifier can predict to which class an instance belongs based on a decision score (a real number) that measures the association of the input with each class.

Common interface for score-based multi-class classifiers. A multi-class classifier can predict to which class an instance belongs based on a decision score (a real number) that measures the association of the input with each class.

Common interface for score-based multi-class classifiers. A multi-class classifier can predict to which class an instance belongs based on a decision score (a real number) that measures the association of the input with each class.

Common interface for multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once.

Common interface for multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once.

Common interface for multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once.

Common interface for generative multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once, as well as their probabilities.

Common interface for generative multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once.

Common interface for generative multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once.

Common interface for generative multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once, as well as their probabilities.

Common interface for score-based multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once based on a decision score (a real number) computed for each class.

Common interface for generative multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once, as well as their probabilities.

Common interface for score-based multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once based on a decision score (a real number) computed for each class.

Common interface for score-based multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once based on a decision score (a real number) computed for each class.

Common interface for score-based multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once based on a decision score (a real number) computed for each class.

Common interface for score-based multi-label classifiers. A multi-label classifier can predict the occurrence of multiple class labels at once based on a decision score (a real number) computed for each class.

Common interface for multiple regression models. Multiple regression models learn how to produce a set of real values (a real-valued vector) from an input vector x.

Common interface for multiple regression models. Multiple regression models learn how to produce a set of real values (a real-valued vector) from an input vector x.

Common interface for data transformation algorithms. Examples of transformations include classifiers, regressions and other machine learning techniques.

Common interface for parallel algorithms.

Common interface for regression models. Regression models learn how to produce a real value (or a set of real values) y from an input vector x.

Common interface for regression models. Regression models learn how to produce a real value (or a set of real values) y from an input vector x.

Common interface for observation sequence taggers.

Common interface for supervised learning algorithms for binary classifiers.

Common interface for supervised learning algorithms for binary classifiers.

Common interface for supervised learning algorithms.

Common interface for supervised learning algorithms for multi-class classifiers.

Common interface for supervised learning algorithms for multi-class classifiers.

Common interface for supervised learning algorithms for multi-label classifiers.

Common interface for supervised learning algorithms for multi-label classifiers.

Common interface for algorithms that can be canceled in the middle of execution.

Common interface for generative observation sequence taggers. A sequence tagger can predict the class label of each individual observation in a input sequence vector.

Common interface for data transformation algorithms. Examples of transformations include classifiers, regressions and other machine learning techniques.

Common interface for data transformation algorithms. Examples of transformations include classifiers, regressions and other machine learning techniques.

Common interface for data transformation algorithms. Examples of transformations include classifiers, regressions and other machine learning techniques.

Common interface for unsupervised learning algorithms.

Obsolete. Please refer to BootstrapTModel, TInput, TOutput instead.

Obsolete. Please use CrossValidationTModel, TInput, TOutput instead.

Delegate for grid search fitting functions.

Obsolete. Please use SplitSetValidationTModel, TInput, TOutput instead.

Obsolete. Please use SplitSetValidationTModel, TInput, TOutput instead.

Weighting schemes for Inverse Document Frequency (IDF).

Modes for storing models.

Initialization schemes for clustering algorithms.

Mini-batch data shuffling options.

Weighting schemes for term-frequency (TF).