Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/43962
Title: One-pass online learning : a local approach
Authors: Zhou, Z
Zheng, WS
Hu, JF
Xu, Y
You, J 
Keywords: Classification
Local modeling
One-pass online learning
Issue Date: 2016
Publisher: Elsevier
Source: Pattern recognition, 2016, v. 51, p. 346-357 How to cite?
Journal: Pattern recognition 
Abstract: Online learning is very important for processing sequential data and helps alleviate the computation burden on large scale data as well. Especially, one-pass online learning is to predict a new coming sample's label and update the model based on the prediction, where each coming sample is used only once and never stored. So far, existing one-pass online learning methods are globally modeled and do not take the local structure of the data distribution into consideration, which is a significant factor of handling the nonlinear data separation case. In this work, we propose a local online learning (LOL) method, a multiple hyperplane Passive Aggressive algorithm integrated with online clustering, so that all local hyperplanes are learned jointly and working cooperatively. This is achieved by formulating a common component as information traffic among multiple hyperplanes in LOL. A joint optimization algorithm is proposed and theoretical analysis on the cumulative error is also provided. Extensive experiments on 11 datasets show that LOL can learn a nonlinear decision boundary, overall achieving notably better performance without using any kernel modeling and second order modeling.
URI: http://hdl.handle.net/10397/43962
ISSN: 0031-3203
EISSN: 1873-5142
DOI: 10.1016/j.patcog.2015.09.003
Appears in Collections:Journal/Magazine Article

SFX Query Show full item record

SCOPUSTM   
Citations

2
Last Week
0
Last month
Citations as of Dec 7, 2017

WEB OF SCIENCETM
Citations

1
Last Week
0
Last month
Citations as of Dec 9, 2017

Page view(s)

75
Last Week
1
Last month
Citations as of Dec 10, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.