Learning from partially supervised data using mixture models and belief functions

DOI10.1016/j.patcog.2008.07.014zbMath1181.68231OpenAlexW2128314196MaRDI QIDQ1005634

Patrice Aknin, Thierry Denoeux, Latifa Oukhellou, Etienne Côme

Publication date: 9 March 2009

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.patcog.2008.07.014

zbMATH Keywords

classificationEM algorithmDempster-Shafer theoryclusteringtransferable belief modelmixture modelssemi-supervised learningpartially supervised learning

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Related Items (26)

Estimating mutual information for feature selection in the presence of label noise ⋮ Parameter estimation based on interval-valued belief structures ⋮ Weighted Maximum Likelihood for Parameters Learning Based on Noisy Labels in Discrete Hidden Markov Models ⋮ Feature selection and disambiguation in learning from fuzzy labels using rough sets ⋮ Variational learning of a Dirichlet process of generalized Dirichlet distributions for simultaneous clustering and feature selection ⋮ Statistical Inference from Ill-known Data Using Belief Functions ⋮ Semi-supervised model-based clustering with positive and negative constraints ⋮ Parametric classification with soft labels using the evidential EM algorithm: linear discriminant analysis versus logistic regression ⋮ SELP: semi-supervised evidential label propagation algorithm for graph data clustering ⋮ An Evidential K-Nearest Neighbor Classifier Based on Contextual Discounting and Likelihood Maximization ⋮ Clustering and classification of fuzzy data using the fuzzy EM algorithm ⋮ A Solution for the Learning Problem in Evidential (Partially) Hidden Markov Models Based on Conditional Belief Functions and EM ⋮ Nonparametric criteria for supervised classification of fuzzy data ⋮ Rough set-based feature selection for weakly labeled data ⋮ Learning from imprecise and fuzzy observations: data disambiguation through generalized loss minimization ⋮ Likelihood-based belief function: justification and some extensions to low-quality data ⋮ Learning from partially supervised data using mixture models and belief functions ⋮ Extending stochastic ordering to belief functions on the real line ⋮ Maximum likelihood estimation from fuzzy data using the EM algorithm ⋮ A new evidential \(K\)-nearest neighbor rule based on contextual discounting with partially supervised learning ⋮ Cautious classification based on belief functions theory and imprecise relabelling ⋮ Belief functions and rough sets: survey and new insights ⋮ The importance of being clustered: uncluttering the trends of statistics from 1970 to 2015 ⋮ Semi-supervised cross-entropy clustering with information bottleneck constraint ⋮ On the relative value of weak information of supervision for learning generative models: an empirical study ⋮ Naive possibilistic classifiers for imprecise or uncertain numerical data

Uses Software

• UCI-ml

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Classification in the presence of class noise using a probabilistic kernel Fisher method
• Learning from partially supervised data using mixture models and belief functions
• Bayesian regularization for normal mixture estimation and model-based clustering
• High-dimensional data clustering
• Uniqueness of information measure in the theory of evidence
• Belief functions: The disjunctive rule of combination and the generalized Bayesian theorem
• The transferable belief model
• Belief function independence: I. The marginal case
• Uncertainty-based information. Elements of generalized information theory
• Belief function independence. II: The conditional case.
• Text classification from labeled and unlabeled documents using EM
• A mathematical theory of arguments for statistical evidence
• Least committed basic belief density induced by a multivariate Gaussian: Formulation with applications
• Pruning belief decision tree methods in averaging and conjunctive approaches
• Decision making on the sole basis of statistical likelihood
• On the plausibility transformation method for translating belief function models to probability models
• Belief functions on real numbers
• A boosting approach to remove class label noise1
• Belief Classification Approach Based on Generalized Credal EM
• On the unicity of dempster rule of combination
• Estimating the Linear Discriminant Function from Initial Samples Containing a Small Number of Unclassified Observations
• Normal Discrimination with Unclassified Observations
• Model-Based Gaussian and Non-Gaussian Clustering
• Finite mixture models
• Upper Probabilities Based Only on the Likelihood Function
• High-Dimensional Discriminant Analysis
• Symbolic and Quantitative Approaches to Reasoning with Uncertainty
• Upper and Lower Probabilities Induced by a Multivalued Mapping
• Advances in Intelligent Data Analysis VI
• Handling possibilistic labels in pattern classification using evidential reasoning.
• Belief decision trees: Theoretical foundations

This page was built for publication: Learning from partially supervised data using mixture models and belief functions