L₂ normalized data clustering through the Dirichlet process mixture model of von Mises distributions with localized feature selection

DOI10.1007/978-3-030-23876-6_6MaRDI QIDQ5110027zbMATH OpenOpenAlexFDO

Authors Wentao Fan, Nizar Bouguila, Ye-Wang Chen, Ziyi Chen

Publication date 15 May 2020

Published in Unsupervised and Semi-Supervised Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-030-23876-6_6

zbMATH Keywords

feature selectionspherical datamixture modelnovelty detectiondata clusteringimage categorizationvon Mises (VM) distribution

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Statistical aspects of big data and data science (62R07) Image analysis in multivariate analysis (62H35)

Recommendations

• scientific article; zbMATH DE number 5430929
• Infinite Dirichlet mixture models learning via expectation propagation
• Hybrid Gaussian and von Mises model-based clustering
• Variational learning of a Dirichlet process of generalized Dirichlet distributions for simultaneous clustering and feature selection
• Directional co-clustering

Cites work

• scientific article; zbMATH DE number 774881 (Why is no real title available?)
• A Bayesian analysis of some nonparametric problems
• An introduction to variational methods for graphical models
• Contributions to the theory of Dirichlet processes
• Finite mixture models
• Pattern recognition and machine learning.
• Unsupervised learning by probabilistic latent semantic analysis
• Variational inference for Dirichlet process mixtures

Cited in

(1)

• Online trans-dimensional von Mises-Fisher mixture models for user profiles

Describes a project that uses

Uses Software

• PRMLT
• Bow
• PCA-SIFT

This page was built for publication: \(L_2\) normalized data clustering through the Dirichlet process mixture model of von Mises distributions with localized feature selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5110027)