Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

Nonlinear Approximation in High-Dimensional Spaces Using Tree-Structured Intelligent Systems

수목구조 지능시스템을 이용한 고차원 공간 위에서의 비선형 근사

  • Published : 1996.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

Conventional radial-basis-function networks and fuzzy systems have serious problems in dealing with the non1inea:r approximations on high-dimensional spaces due to the explosive increase of the number of hidden nodes or fuzzy IF-THEN rules. In order to avoid such problems, this paper proposes a tree-structured intelligent system in which semi-local basis functions form its basic elements, and develops a training algorithm for the proposed system based on the modified genetic algorithm and LMS rule. Theoretical analysis is performed on the approximation capability of the proposed system, together with experimental studies which demonstrate the effectiveness of the developed methodology.

기존의 RBF 신경망 및 퍼지 시스템을 고차원 입력 공간 위에서의 비선형 근사에 적용할 경우 은닉 노드의 수혹은 퍼지 IF-THEN 규칙의 수가 기하급수적으로 증가한다. 본 논문에서는 이러한 문제점을 개선하기 위해 반국소 유닛을 기본 요소로 하는 수목구조지능시스템을 제안하고, 이를 효과적으로 학습하기 위하여 수정 유전자 알고리즘 및 LMS 규칙에 기반을 둔 학습 알고리즘을 개발한다. 제안된 시스템에 대한 근사 능력 해석이 수행되고, 실험적 고찰을 통하여 개발된 방법론의 유용성이 입증된다.

Keywords

References

  1. Mathematics of Control, Signals, and Systems v.2 Approximation by superpositon of a sigmoidal function G.Cybenko
  2. Neural Networks v.2 Multilayer feedforward networks K.Hornik;M.Stinchcombe;H.White
  3. Neural Networks v.5 no.1 Approximation of continuous functions on Rd by linear combinations of shifted rotations of a sigmoid function with and without scaling Y.Ito
  4. Neural Computation v.3 Universal approximation using radial basis function networks J.Park;I.W.Sandberg
  5. Neural Computation v.5 Approximation and radial basis function networks J.Park;I.W.Sandberg
  6. Proceedings of the IEEE v.78 Networks for approximation and learning T.Poggio;F.Girosi
  7. Neural Computation v.1 no.2 Fast learning in networks of locally-tuned processing units J.Moody;C.J.Darken
  8. International Journal of Systems Science v.21 no.12 Nonlinear systems identification using radial basis functions S.Chen;S.A.Bliings;C.F.N.Cowan;P.M.Grant
  9. International Journal of Control v.52 no.6 Practical identification of NARMAX models using radial basis funtions S.Chen;S.A.Bliings;C.F.N.Cowan;P.M.Grant
  10. IEEE Transactions on Neural Networks v.4 Functional equivalence between radial basis function networks and fuzzy inference systems J.R.Jang;C.Sun
  11. IEEE Transactions on Fuzzy Systems v.1 no.4 Learning control using fuzzified self-organizing radial basis function network J.Nie;D.A.Linkens
  12. IEEE Transactions on Neural Networks v.1 no.1 A fuzzy logic based approach to qualitative modeling M.Sugeno;T.Yasukawa
  13. IFSA'93 Structures for building flexible neural fuzzy systems R.Yager
  14. Ph. D. Dissertation, Florida State University Intelligent fuzzy reasoning models with application fo fuzzy control D.Park
  15. IEEE Transactions on Systems, Man and Cybernetics Genetic-based new fuzzy reasoning models with application to fuzzy control D.Park;A.Kandel;G.Langholz
  16. Second IEEE International Conference on Fuzzy Systems v.1 Integrationg design stages of fuzzy systems using genetic algorithms M.A.Lee;H.Takagi
  17. Proceedings of Third IEEE International Conference on Fuzzy Systems Design of sophisticated fuzzy logic controllers using genetic algorithms K.C.Ng;Y.Li
  18. Neural Computation v.3 no.1 A Tree-structured algorithm for reducing computation in networks with separable basis functions T.D.Sanger
  19. IEEE Transactions on Neural Networks v.2 no.2 A tree-structured adaptive network for function approximation in high-dimensional spaces T.D.Sanger
  20. Genetic Algorithms + Data Structures=Evolution Programs, Second , Extended Edition Z.Michaelewicz
  21. Fuzzy Sets and Systems v.53 Sugeno type controllers are universal controllers J.J.Buckley
  22. Fuzzy Sets and Systems v.58 Fuzzy input-output controllers are universal approximators J.J.Buckley;Y.Hayashi
  23. Circuits, Systems and Signal Processing v.13 no.1 Nonlinear approximation using elliptic basis function networks J.Park;I.W.Sandberg
  24. Adative fuzzy systems and control: Design and stability analysis L.Wang
  25. IEEE Transactions on Systems,Man, and Cybernetics v.22 no.6 Generationg fuzzy rules from numerical data, with applications L.Wang;J.M.Mendel