The Wolfram Language offers a rich selection of machine learning methods to perform regression, classification, clustering, dimensionality reduction and more.

Classification (Classify)

"ClassDistributions" — use learned distributions

"DecisionTree" — use a decision tree

"GradientBoostedTrees" — use an ensemble of trees trained with gradient boosting

"LogisticRegression" — use probabilities from linear combinations of features

"Markov" — use a Markov model on the feature sequence (only for text, bag of tokens, ...)

"NaiveBayes" — classify by assuming probabilistic independence of features

"NearestNeighbors" — use nearest-neighbor examples

"NeuralNetwork" — use artificial neural networks

"RandomForest" — use Breiman–Cutler ensembles of decision trees

"SupportVectorMachine" — use a support vector machine

Regression (Predict)

"DecisionTree" — use a decision tree

"GradientBoostedTrees" — use an ensemble of trees trained with gradient boosting

"LinearRegression" — use a linear combination of features

"NearestNeighbors" — use nearest-neighbor examples

"NeuralNetwork" — use artificial neural networks

"RandomForest" — use Breiman–Cutler ensembles of decision trees

"GaussianProcess" — use a Gaussian process prior over functions

Clustering (FindClusters)

"Agglomerate" — single linkage clustering algorithm

"DBSCAN" — density-based spatial clustering of applications with noise

"GaussianMixture" — use a mixture of Gaussian (normal) distributions

"JarvisPatrick" — Jarvis–Patrick clustering algorithm

"KMeans" — k-means clustering algorithm

"KMedoids" — partitioning around medoids

"MeanShift" — mean-shift clustering algorithm

"NeighborhoodContraction" — shift data points toward high-density regions

"SpanningTree" — minimum spanning tree–based clustering algorithm

"Spectral" — spectral clustering algorithm

Distribution Modeling (LearnDistribution)

"ContingencyTable" — discretize data and store each possible probability

"DecisionTree" — use a decision tree

"GaussianMixture" — use a mixture of Gaussian (normal) distributions

"KernelDensityEstimation" — use a kernel mixture distribution

"Multinormal" — use a multivariate normal (Gaussian) distribution

Dimensionality Reduction (DimensionReduction)

"Autoencoder" — use a trainable autoencoder

"Hadamard" — project data using a Hadamard matrix

"Isomap" — isometric mapping

"LatentSemanticAnalysis" — latent semantic analysis method

"Linear" — automatically choose the best linear method

"LLE" — locally linear embedding

"PrincipalComponentsAnalysis" — principal components analysis method

"MultidimensionalScaling" — metric multidimensional scaling

"TSNE" — t-distributed stochastic neighbor embedding algorithm

"UMAP" — uniform manifold approximation and projection