The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Support Vector Machines Controlling Noise Influence Effectively

서포트 벡터 기계에서 잡음 영향의 효과적 조절

  • Kim, Chul-Eung (Dept. of Applied Statistics, Yonsei University) ;
  • Yoon, Min (Dept. of Applied Statistics, Yonsei University)
  • 김철응 (연세대학교 응용통계학과) ;
  • 윤민 (연세대학교 응용통계학과)
  • Published : 2003.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

Support Vector Machines (SVMs) provide a powerful performance of the learning system. Generally, SVMs tend to make overfitting. For the purpose of overcoming this difficulty, the definition of soft margin has been introduced. In this case, it causes another difficulty to decide the weight for slack variables reflecting soft margin classifiers. Especially, the error of soft margin algorithm can be bounded by a target margin and some norms of the slack vector. In this paper, we formulate a new soft margin algorithm considering the bound of corruption by noise in data directly. Additionally, through a numerical example, we compare the proposed method with a conventional soft margin algorithm.

서포트 벡터 기계(Support Vector Machines, SVMs)에서의 일반화 오차의 경계는 훈련점들과 분리 초평면 사이의 최소의 거리에 의존한다. 특히, 소프트 마진 알고리즘은 목표 마진과 slack 벡터의 놈들에 의하여 경계가 결정된다. 이 논문에서는, 자료들에 있어서 잡음들에 의한 오염들을 직접적으로 고려하는 새로운 소프트 마진 알고리즘을 공식화하였다. 그리고, 수치적 예제를 통하여, 제안된 방법과 기존의 소프트 마진 알고리즘을 비교하였다.

Keywords

References

  1. Advances in Kernel Methods-Support Vector learning Generalization Performance of Support Vector Machines an Other Pattern Classifiers Bartlett,P.;Shawe-Taylor,J.;Sch$\ "{o}$lkopf,B.(ed.);Burges,C.J.C.(ed.);Smola,A.(ed.)
  2. Learning from Data: Concepts, Theory, and methods Cherkassky,V.;Mulier,F.
  3. An Introduction to Support Vector Machines and other kernel-based learning methods Cristianini,N.;Shawe-Taylor,J.
  4. Applied Multivariate Statistical Analysis(3rd ed.) Johnson,R.A.;Wichern,D.W.
  5. Advances in Large Margin Classifiers Generalized Support Vector Machines Mangasarian,O.L.;Smola,A.(ed.);Bartlett,B.(ed.);Sch$\ "{o}$lkopf,B.(ed.);Schuurmans,D.(ed.)
  6. NeuroCOLT2 Technical Report Series, NC-TR-2000-082 On the generalization of Soft margin Algorithms Shawe-Taylor,J.;Cristianini,N.
  7. NeuroCOLT2 Technical Report A Tutorial on Support Vector Regression Smola,A.J.;Sch$\ "{o}$lkopf,B.
  8. Statistical Learning Theory Vapnik,V.