Skip to main content

Research Repository

Advanced Search

A lossless online Bayesian classifier.

Nguyen, Thi Thu Thuy; Nguyen, Tien Thanh; Sharma, Rabi; Liew, Alan Wee-Chung

Authors

Thi Thu Thuy Nguyen

Rabi Sharma

Alan Wee-Chung Liew



Abstract

We are living in a world progressively driven by data. Besides the issue that big data cannot be entirely stored in the main memory as required by traditional offline learning methods, the problem of learning data that can only be collected over time is also very prevalent. Consequently, there is a need of online methods which can handle sequentially arriving data and offer the same accuracy as offline methods. In this paper, we introduce a new lossless online Bayesian-based classifier which uses the arriving data in a 1-by-1 manner and discards each data right after use. The lossless property of our proposed method guarantees that it can reach the same prediction performance as its offline counterpart regardless of the incremental training order. Experimental results demonstrate its superior performance over many well-known state-of-the-art online learning methods in the literature.

Citation

NGUYEN, T.T.T., NGUYEN, T.T., SHARMA, R. and LIEW, A. W.-C. 2019. A lossless online Bayesian classifier. Information sciences [online], 489, pages 1-17. Available from: https://doi.org/10.1016/j.ins.2019.03.031

Journal Article Type Article
Acceptance Date Mar 15, 2019
Online Publication Date Mar 16, 2019
Publication Date Jul 31, 2019
Deposit Date Apr 23, 2019
Publicly Available Date Mar 17, 2020
Journal Information Sciences
Print ISSN 0020-0255
Electronic ISSN 1872-6291
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 489
Pages 1-17
DOI https://doi.org/10.1016/j.ins.2019.03.031
Keywords Online learning; Lossless methods; Online classifiers; Bayesian method; Variational inference; Multivariate gaussiane
Public URL https://rgu-repository.worktribe.com/output/238169

Files




You might also like



Downloadable Citations