Main Content

La traducción de esta página aún no se ha actualizado a la versión más reciente. Haga clic aquí para ver la última versión en inglés.

Clasificación de máquinas de vectores de apoyo

Máquinas de vectores de apoyo para clasificación binaria o multiclase

Para aumentar la precisión y las opciones de funciones de kernel en conjuntos de datos de dimensiones bajas y medianas, entrene un modelo SVM binario o un modelo multiclase de códigos de salida de corrección de errores (ECOC, por sus siglas en inglés) que contenga modelos de aprendizaje binarios SVM utilizando la app Classification Learner. Para mayor flexibilidad, utilice la interfaz de línea de comandos para entrenar un modelo SVM binario mediante fitcsvm o un modelo ECOC multiclase compuesto por modelos de aprendizaje binarios SVM mediante fitcecoc.

Para reducir el tiempo de proceso en conjuntos de datos de altas dimensiones, entrene de forma eficiente un modelo de clasificación lineal binaria, por ejemplo, un modelo SVM lineal, mediante fitclinear o entrene un modelo ECOC multiclase compuesto por modelos SVM mediante fitcecoc.

Para las clasificaciones no lineales con big data, entrene un modelo de clasificación binaria de kernel gaussiano mediante fitckernel.

Apps

Classification LearnerEntrenar modelos para clasificar datos usando machine learning supervisado

Bloques

ClassificationSVM PredictClassify observations using support vector machine (SVM) classifier for one-class and binary classification (desde R2020b)
ClassificationECOC PredictClassify observations using error-correcting output codes (ECOC) classification model (desde R2023a)
ClassificationLinear PredictClassify observations using linear classification model (desde R2023a)
IncrementalClassificationLinear PredictClassify observations using incremental linear classification model (desde R2023b)
IncrementalClassificationLinear FitFit incremental linear binary classification model (desde R2023b)
Update MetricsUpdate performance metrics in incremental learning model given new data (desde R2023b)

Funciones

expandir todo

Crear un modelo o plantilla

fitcsvmTrain support vector machine (SVM) classifier for one-class and binary classification
compactReduce size of machine learning model
templateSVMSupport vector machine template

Modificar un modelo

discardSupportVectorsDiscard support vectors for linear support vector machine (SVM) classifier
incrementalLearnerConvert binary classification support vector machine (SVM) model to incremental learner (desde R2020b)
resumeResume training support vector machine (SVM) classifier

Interpretar un modelo

limeLocal interpretable model-agnostic explanations (LIME) (desde R2020b)
partialDependenceCompute partial dependence (desde R2020b)
plotPartialDependenceCreate partial dependence plot (PDP) and individual conditional expectation (ICE) plots
shapleyShapley values (desde R2021a)

Realizar una validación cruzada

crossvalCross-validate machine learning model
kfoldEdgeClassification edge for cross-validated classification model
kfoldLossClassification loss for cross-validated classification model
kfoldMarginClassification margins for cross-validated classification model
kfoldPredictClassify observations in cross-validated classification model
kfoldfunCross-validate function for classification

Medir el rendimiento

lossFind classification error for support vector machine (SVM) classifier
resubLossResubstitution classification loss
compareHoldoutCompare accuracies of two classification models using new data
edgeFind classification edge for support vector machine (SVM) classifier
marginFind classification margins for support vector machine (SVM) classifier
resubEdgeResubstitution classification edge
resubMarginResubstitution classification margin
testckfoldCompare accuracies of two classification models by repeated cross-validation
fitSVMPosteriorFit posterior probabilities
fitPosteriorFit posterior probabilities for compact support vector machine (SVM) classifier

Clasificar observaciones

predictClassify observations using support vector machine (SVM) classifier
resubPredictClassify training data using trained classifier

Recopilar propiedades de un modelo

gatherGather properties of Statistics and Machine Learning Toolbox object from GPU (desde R2020b)
fitclinearFit binary linear classifier to high-dimensional data
predictPredict labels for linear classification models
templateLinearLinear learner template
fitckernelFit binary Gaussian kernel classifier using random feature expansion
predictPredict labels for Gaussian kernel classification model
templateKernelKernel learner template
fitcecocFit multiclass models for support vector machines or other classifiers
predictClassify observations using multiclass error-correcting output codes (ECOC) model
templateECOCError-correcting output codes learner template

Clases

expandir todo

ClassificationSVMSupport vector machine (SVM) for one-class and binary classification
CompactClassificationSVMCompact support vector machine (SVM) for one-class and binary classification
ClassificationPartitionedModelCross-validated classification model
ClassificationLinearLinear model for binary classification of high-dimensional data
ClassificationPartitionedLinearCross-validated linear model for binary classification of high-dimensional data
ClassificationKernelGaussian kernel classification model using random feature expansion
ClassificationPartitionedKernelCross-validated, binary kernel classification model
ClassificationECOCMulticlass model for support vector machines (SVMs) and other classifiers
CompactClassificationECOCCompact multiclass model for support vector machines (SVMs) and other classifiers
ClassificationPartitionedECOCCross-validated multiclass ECOC model for support vector machines (SVMs) and other classifiers
ClassificationPartitionedLinearECOCCross-validated linear error-correcting output codes model for multiclass classification of high-dimensional data
ClassificationPartitionedKernelECOCCross-validated kernel error-correcting output codes (ECOC) model for multiclass classification

Temas