Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

A New Design Method for the GBAM (General Bidirectional Associative Memory) Model

GBAM 모델을 위한 새로운 설계방법

  • 박주영 (고려대학교 제어계측공학과) ;
  • 임채환 (고려대학교 제어계측공학과) ;
  • 김혜연 (삼성전자 소프트웨어센터 HCI 파트)
  • Published : 2001.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a new design method for the GBAM: (general bidirectional associative memory) model. Based on theoretical investigations on the GBAM: model, it is shown that the design of the GBAM:-based bidirectional associative memeories can be formulated as optimization problems called GEVPs (generalized eigenvalue problems). Since the GEVPs arising in the procedure can be efficiently solved within a given tolerance by the recently developed interior point methods, the design procedure established in this paper is very useful in practice. The applicability of the proposed design procedure is demonstrated by simple design examples considered in related studies.

본 논문은 GBAM (general bidirectional associative memory) 모델을 위한 새로운 설계방법을 제시한다. GBAM 모델에 대한 이론적 고찰을 바탕으로, GBAM 기방 양방향 연상 메모리의 설계 문제가 GEVP (generalized eigenvalue problem)로 불리는 최적화 문제로 표현될 수 있음을 밝힌다. 설계 과정에서 등장하는 GEVP 문제들은 최근에 개발된 내부점 방법에 의하여 주어진 허용 오차 이내에서 효과적으로 풀릴 수 있으므로, 본 논문에서 확립된 설계 절차는 매우 실용적이다. 제안된 설계 절차에 대한 적용 가능성은 관련 연구에서 고려되었던 간단한 설계 예제를 통하여 예시된다.

Keywords

References

  1. Neurocomputing: Foundations of Rearch Distinctive features, categorical perception, and probability learning: Some applications of a neural model J. A. Anderson;J. W. Silverstein;S. A. Ritz;R. S. Jones;J. A. Anderson(eds.);E. Rosenfeld(eds.)
  2. Fundamentals of Artficial neural networks M. H. Hassoun
  3. Proc. Nat. Acad. Sciences v.79 Neural networks and physical systems with emergent collective computational abilities J. J. Hopfield
  4. IEEE Trans. Syst., Man, and Cybern. v.18 Bidirectional Associative Memories B. Kosko
  5. IEEE Contr. Syst. Mag. v.10 Associative Memories via Artificial Neural Networks A. N. Michel;J. A. Farrell
  6. IEEE Trans. Neural Networks v.1 Two coding strategies for bidirectional associative memory Y. F. Wang;J. B. Cruz;J. H. Mulligan
  7. IEEE Trans. Neural Networks v.2 Gu aranteed recall of all training pairs for bidirectional associative memory Y. F. Wang;J. B. Cruz;J. H. Mulligan
  8. IEEE Trans. Neural Networks. v.5 Multilayer associative neural networks (MANN's): Storage capacity versus perfect recall H. Kang
  9. International J. Syst. Science v.28 Genetic approach to the design of bidirectional associative memory G. Shi
  10. IEEE Trans. Syst., Man, Cybern. v.24 Designing bidirectional associative memories with optimal stability T. Wang;X. Zhuang;X. Xing
  11. Neural Networks v.10 complexity preserving increase of the capacity of bidirectional associative memories by dilation and translation B. Lenze
  12. IEEE Trans. Syst., Man, Cybern.-Part B v.28 A general model for bidirectional associative memories H. Shi;Y. Zhao;X. Zhuang
  13. IEEE Trans. Syst., Man, Cybern. v.45 Asymmetric bidirectional associative memories Z.-B. Xu;Y. Leung;X.-W. He
  14. Neural Networks v.6 Better learning for bidirectional associative memory X. Zhuang;Y. Huang;S.-S. Chen
  15. Linear matrix inequalities in systems and control theory, S. Boyd;L. El Ghaoui;E. Feron;V. Balakrishnan
  16. IEEE Contral Syst. Magazine v.17 Algorithms and software for LMI problems in control L. Vandenberghe;V. Balakrishnan
  17. LMI Control Toolbox P. Gahinet;A. Nemirivskii;A. J. Laub;M Chilali