Please use this identifier to cite or link to this item: https://doi.org/10.1109/72.822516
Title: A fast iterative nearest point algorithm for support vector machine classifier design
Authors: Keerthi, S.S. 
Shevade, S.K.
Bhattacharyya, C.
Murthy, K.R.K.
Keywords: Classification
Nearest point algorithm
Quadratic programming
Support vector machine
Issue Date: Jan-2000
Source: Keerthi, S.S., Shevade, S.K., Bhattacharyya, C., Murthy, K.R.K. (2000-01). A fast iterative nearest point algorithm for support vector machine classifier design. IEEE Transactions on Neural Networks 11 (1) : 124-136. ScholarBank@NUS Repository. https://doi.org/10.1109/72.822516
Abstract: In this paper we give a new fast iterative algorithm for support vector machine (SVM) classifier design. The basic problem treated is one that does not allow classification violations. The problem is converted to a problem of computing the nearest point between two convex polytopes. The suitability of two classical nearest point algorithms, due to Gilbert, and Mitchell et al., is studied. Ideas from both these algorithms are combined and modified to derive our fast algorithm. For problems which require classification violations to be allowed, the violations are quadratically penalized and an idea due to Cortes and Vapnik and Frieß is used to convert it to a problem in which there are no classification violations. Comparative computational evaluation of our algorithm against powerful SVM methods such as Platt's sequential minimal optimization shows that our algorithm is very competitive. © 2000 IEEE.
Source Title: IEEE Transactions on Neural Networks
URI: http://scholarbank.nus.edu.sg/handle/10635/54135
ISSN: 10459227
DOI: 10.1109/72.822516
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

228
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

185
checked on Nov 16, 2017

Page view(s)

20
checked on Dec 10, 2017

Google ScholarTM

Check

Altmetric


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