Proceedings of the 3rd International Conference on Computer Science and Service System

Fast Incremental SVM Learning Algorithm based on Center Convex Vector

Authors
Bai DongYing, Han Jun, Zhang Ci
Corresponding Author
Bai DongYing
Available Online June 2014.
DOI
https://doi.org/10.2991/csss-14.2014.11How to use a DOI?
Keywords
support vector machine; incremental learning; convex hull operator;
Abstract

A fast SVM learning algorithm is proposed according to incremental learning and center convex hull operator. It is established on analyzing the relevance of support vector and convex hull from the angle of calculation geometry. The convex hull of current training samples is solved in the first place. Further, Euclidean distance elimination is applied to convex hull. Meanwhile, every time when the incremental learning is going on, the training samples should contain samples violated KKT condition in previous sample set, experiment results indicate that the algorithm effectively shortens training time while classification accuracy keep a satisfied level.

Copyright
© 2014, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 3rd International Conference on Computer Science and Service System
Series
Advances in Intelligent Systems Research
Publication Date
June 2014
ISBN
10.2991/csss-14.2014.11
ISSN
1951-6851
DOI
https://doi.org/10.2991/csss-14.2014.11How to use a DOI?
Copyright
© 2014, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Bai DongYing
AU  - Han Jun
AU  - Zhang Ci
PY  - 2014/06
DA  - 2014/06
TI  - Fast Incremental SVM Learning Algorithm based on Center Convex Vector
BT  - Proceedings of the 3rd International Conference on Computer Science and Service System
PB  - Atlantis Press
SP  - 42
EP  - 45
SN  - 1951-6851
UR  - https://doi.org/10.2991/csss-14.2014.11
DO  - https://doi.org/10.2991/csss-14.2014.11
ID  - DongYing2014/06
ER  -