An efficient method for simplifying decision functions of support vector machines

Jun Guo; Norikazu Takahashi; Tetsuo Nishi

doi:10.1093/ietfec/e89-a.10.2795

An efficient method for simplifying decision functions of support vector machines

Jun Guo, Norikazu Takahashi, Tetsuo Nishi

Research output: Contribution to journal › Article › peer-review

15 Citations (Scopus)

Abstract

A novel method to simplify decision functions of support vector machines (SVMs) is proposed in this paper. In our method, a decision function is determined first in a usual way by using all training samples. Next those support vectors which contribute less to the decision function are excluded from the training samples. Finally a new decision function is obtained by using the remaining samples. Experimental results show that the proposed method can effectively simplify decision functions of SVMs without reducing the generalization capability.

Original language	English
Pages (from-to)	2795-2802
Number of pages	8
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E89-A
Issue number	10
DOIs	https://doi.org/10.1093/ietfec/e89-a.10.2795
Publication status	Published - Oct 2006
Externally published	Yes

Keywords

Complexity
Decision function
Span
Support vector machines

ASJC Scopus subject areas

Signal Processing
Computer Graphics and Computer-Aided Design
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1093/ietfec/e89-a.10.2795

Cite this

@article{69f6eabc59f84eb0ba29a9502503e4d3,

title = "An efficient method for simplifying decision functions of support vector machines",

abstract = "A novel method to simplify decision functions of support vector machines (SVMs) is proposed in this paper. In our method, a decision function is determined first in a usual way by using all training samples. Next those support vectors which contribute less to the decision function are excluded from the training samples. Finally a new decision function is obtained by using the remaining samples. Experimental results show that the proposed method can effectively simplify decision functions of SVMs without reducing the generalization capability.",

keywords = "Complexity, Decision function, Span, Support vector machines",

author = "Jun Guo and Norikazu Takahashi and Tetsuo Nishi",

year = "2006",

month = oct,

doi = "10.1093/ietfec/e89-a.10.2795",

language = "English",

volume = "E89-A",

pages = "2795--2802",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "10",

}

TY - JOUR

T1 - An efficient method for simplifying decision functions of support vector machines

AU - Guo, Jun

AU - Takahashi, Norikazu

AU - Nishi, Tetsuo

PY - 2006/10

Y1 - 2006/10

N2 - A novel method to simplify decision functions of support vector machines (SVMs) is proposed in this paper. In our method, a decision function is determined first in a usual way by using all training samples. Next those support vectors which contribute less to the decision function are excluded from the training samples. Finally a new decision function is obtained by using the remaining samples. Experimental results show that the proposed method can effectively simplify decision functions of SVMs without reducing the generalization capability.

AB - A novel method to simplify decision functions of support vector machines (SVMs) is proposed in this paper. In our method, a decision function is determined first in a usual way by using all training samples. Next those support vectors which contribute less to the decision function are excluded from the training samples. Finally a new decision function is obtained by using the remaining samples. Experimental results show that the proposed method can effectively simplify decision functions of SVMs without reducing the generalization capability.

KW - Complexity

KW - Decision function

KW - Span

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=33750069471&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750069471&partnerID=8YFLogxK

U2 - 10.1093/ietfec/e89-a.10.2795

DO - 10.1093/ietfec/e89-a.10.2795

M3 - Article

AN - SCOPUS:33750069471

SN - 0916-8508

VL - E89-A

SP - 2795

EP - 2802

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 10

ER -

An efficient method for simplifying decision functions of support vector machines

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this