상세정보

INTRODUCTIONA brief history Semisupervised learning Organization and assumptionsSELF-TRAINING AND CO-TRAINING Classification Self-training Co-trainingAPPLICATIONS OF SELF-TRAINING AND CO-TRAINING Part-of-speech tagging Information extraction Parsing Word sensesCLASSIFICATION Two simple classifiers Abstract setting Evaluating detectors and classifiers that abstain Binary classifiers and ECOCMATHEMATICS FOR BOUNDARY-ORIENTED METHODS Linear separators The gradient Constrained optimizationBOUNDARY-ORIENTED METHODS The perceptron Game self-teaching Boosting Support vector machines (SVMs)Null-category noise modelCLUSTERING Cluster and label Clustering conceptsHierarchical clustering Self-training revisited Graph mincut Label propagation Bibliographic notesGENERATIVE MODELSGaussian mixturesThe EM algorithmAGREEMENT CONSTRAINTS Co-trainingAgreement-based self-teaching Random fieldsBibliographic notesPROPAGATION METHODS Label propagation Random walks Harmonic functionsFluidsComputing the solution Graph mincuts revisited Bibliographic notesMATHEMATICS FOR SPECTRAL METHODS Some basic conceptsEigenvalues and eigenvectorsEigenvalues and the scaling effects of a matrixBibliographic notesSPECTRAL METHODSSimple harmonic motionSpectra of matrices and graphsSpectral clusteringSpectral methods for semisupervised learningBibliographic notesBIBLIOGRAPHY INDEX

정보제공 :