Journal Article10.1016/J.PATCOG.2008.01.025
Non-stationary data sequence classification using online class priors estimation
Chunyu Yang,Jie Zhou +1 more
34
TL;DR: Inspired by the offline iterative EM algorithm for static data sets, this paper proposes an online incremental EM algorithm to estimate the class priors along the data sequence and shows that the proposed algorithm indeed performs better than the conventional offline iteratives EM algorithm when theclass priors are non-stationary.
read more
About: This article is published in Pattern Recognition. The article was published on 01 Aug 2008. The article focuses on the topics: Online algorithm & Iterative method.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Jian Liang,Ran He,Tien-Ping Tan +2 more
TL;DR: Test-time adaptation (TTA) as discussed by the authors has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions, which is an emerging paradigm.
107
Quantification and semi-supervised classification methods for handling changes in class distribution
Jack Chongjie Xue,Gary M. Weiss +1 more
- 28 Jun 2009
TL;DR: This paper designs and evaluates a number of methods for coping with the problem where the class distribution changes and only unlabeled examples are available from the new distribution and introduces a hybrid method that utilizes both quantification and semi-supervised learning.
A Comprehensive Survey on Test-Time Adaptation Under Distribution Shifts
Jian Liang,Ran He,Tieniu Tan +2 more
47
F-NSP+: A fast negative sequential patterns mining method with self-adaptive data storage
TL;DR: A fast NSP mining algorithm, f-NSP, is proposed, which uses a bitmap to store the PSP’s information and then obtain the support of NSC only by bitwise operations, which is much faster than the hash method in e-N SP.
43
Classification in Presence of Drift and Latency
Georg Krempl,Vera Hofer +1 more
- 11 Dec 2011
TL;DR: An exemplary drift-adaptive learning strategy that employs an explicit models of drift, which can be employed when actual, labelled data is scarce or not available at all, as they allow to anticipate changes in distributions over time.
34
References
•Proceedings Article
Transductive Inference for Text Classification using Support Vector Machines
Thorsten Joachims
- 27 Jun 1999
TL;DR: An analysis of why Transductive Support Vector Machines are well suited for text classi cation is presented, and an algorithm for training TSVMs, handling 10,000 examples and more is proposed.
3.3K
An empirical comparison of supervised learning algorithms
Rich Caruana,Alexandru Niculescu-Mizil +1 more
- 25 Jun 2006
TL;DR: A large-scale empirical comparison between ten supervised learning methods: SVMs, neural nets, logistic regression, naive bayes, memory-based learning, random forests, decision trees, bagged trees, boosted trees, and boosted stumps is presented.
A view of the EM algorithm that justifies incremental, sparse, and other variants
Radford M. Neal,Geoffrey E. Hinton +1 more
- 26 Mar 1998
TL;DR: In this paper, an incremental variant of the EM algorithm is proposed, in which the distribution for only one of the unobserved variables is recalculated in each E step, which is shown empirically to give faster convergence in a mixture estimation problem.
2.6K
•Proceedings Article
On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes
Andrew Y. Ng,Michael I. Jordan +1 more
- 03 Jan 2001
TL;DR: It is shown, contrary to a widely-held belief that discriminative classifiers are almost always to be preferred, that there can often be two distinct regimes of performance as the training set size is increased, one in which each algorithm does better.