Advertisement

Multi-Modal System Identifications by a Learning Procedure

  • Setsuzo Tsuji
  • Kousuke Kumamaru
  • Naotoshi Maeda
  • Katsuji Tsuruda

Abstract

The multi-modal search is one of the most important and interesting problems in the field of learning control because this might offer the basic guide to solving many scientific or industrial problems accompanying the optimization. Among many approaches to the multi-modal search, (1)–(4) the method due to the global function learning is considered as the fundamental one since this can obtain the total aspect of performance ranging over the significant domain, in which the information about local extremal points is also included. The straightforward method of function learning will be the estimation of parameters included in the assumptive function representing that multi-modal system.

Keywords

Gaussian Function Function Learning Order Filter Multimodal Function Conditional Probability Density 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. (1).
    K. Nakamura, M. Oda: “Heuristic and Learning Control”, Proceedings of the Japan-U.S. Seminar on Learning Process in Control Systems, Pattern Recognition and Machine Learning, Plenum Pub. Co. (1971).Google Scholar
  2. (2).
    K. Asai, S. Kitajima: “Learning Control of Multimodal Systems by Fuzzy Automata”, ditto.Google Scholar
  3. (3).
    N. Okino, Y. Sakai: “A Method for Separating Every Peak from Multimodal Function Using Monte Carlo Integration”, Trans, of the Society of Instrument and Control Engineers, Vol. 8, No. 6, (1972).Google Scholar
  4. (4).
    K. Kubota: “A New Maximum Searching Method for Unknown One- dimensional Multimodal Function”, Trans, of the Society of Instrument and Control Engineers, Vol. 9, No. 4, (1973;Google Scholar
  5. (5).
    S. Tsuji, K. Kumamaru: “System Identifications by a Nonlinear Filter”, Proceedings of the Japan-U.S. Seminar on Learning Process in Control Systems, Pattern Recognition and Machine Learning, Plenum Pub. Co. (1971).Google Scholar
  6. (6).
    S. Tsuji, K. Kumamaru: “System Identifications and Function Learnings by a Nonlinear Filter”, Memoires of the Faculty of Engineering, Kyushu University, Vol. 30, No. 4, (1971).Google Scholar
  7. (7).
    H. Cox: “On the Estimation of State Variables and Parameters for Noisy Dynamic Systems”, IEEE Trans, on AC, Vol. AC-9, No. 1, (1964).Google Scholar
  8. (8).
    R. Fletcher, M.J.D. Powell: “A Rapidly Convergent Method for Minimization”, Computer J., Vol. 6, No. 2, (1964).Google Scholar
  9. (9).
    A.V. Fiacco, G.P. McCormic: “The Sequential Unconstrained Minimization Technique for Nonlinear Programming”, Management Science, Vol. 10, No. 2, (1964).Google Scholar
  10. (10).
    J. Kowalik, M.R. Osbone: “Methods for Unconstrained Optimization Problems”, American Elserver Pub. Co. (1968).Google Scholar
  11. (11).
    H.J. Kushner: “On the Differential Equations Satisfied by Conditional Probability Densities of Markov Processes”, SIAM J. Control, Series A, Vol. 2, No. 1, (1967).Google Scholar
  12. (12).
    H.J. Kushner: “Dynamical Equations for Optimal Nonlinear Filtering”, J. of Differential Equations, Vol. 3, (1967).Google Scholar
  13. (13).
    H.J. Kushner: “Approximations to Optimal Nonlinear Filters”, IEEE Trans, on AC, Vol. AC-12, No. 5, (1967).Google Scholar
  14. (14).
    D.L. Alspac, H.W. Sorenson: “Nonlinear Bayesian Estimation Using Gaussian Sum Approximation”, IEEE Trans, on AC, Vol. AC-17, No. 4, (1972).Google Scholar
  15. (15).
    S. Tsuji, H. Takata: “The Discrete Nonlinear Estimation Theory by Using the Orthogonal Projection Method”, Memoires of the Faculty of Engineering, Kyushu University, Vol. 22, No. 1, (1972).Google Scholar
  16. (16).
    S. Tsuji, M. Nakamura: “Nonlinear Filter Using a Statistical Processing Technique”, Trans, of the Institute of Electrical Engineers of Japan, Vol. 93-C, No. 5, (1973).Google Scholar
  17. (17).
    S. Tsuji, N. Maeda: “On the Extrema Search of Unknown Multimodal Function by Nonlinear Filter”, Technology Reports of the Kyushu University, Vol. 46, No. 4, (1973).Google Scholar

Copyright information

© Plenum Press, New York 1974

Authors and Affiliations

  • Setsuzo Tsuji
    • 1
  • Kousuke Kumamaru
    • 1
  • Naotoshi Maeda
    • 1
  • Katsuji Tsuruda
    • 1
  1. 1.Kyushu UniversityFukuokaJapan

Personalised recommendations