跳到主要內容

簡易檢索 / 詳目顯示

回結果列表
研究生： 蔡炎龍
Tsai, Yen Lung
論文名稱： 動態徑向基底函數網路與混沌預測
Dynamical Radial Basis Function Networks and Chaotic Forecasting
指導教授： 劉文卿
Liu, Wen Tsin
學位類別： 碩士
Master
系所名稱： 理學院 - 應用數學系
Department of Mathematical Sciences
論文出版年： 1993
畢業學年度： 82
語文別： 英文
論文頁數： 30
中文關鍵詞： 神經網路 、徑向基底函數 、函數逼近 、混沌預測
外文關鍵詞： neural networks, radial basis functions, chaotic forecasting
相關次數： 點閱：291  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 在許多的研究和應用之中都需要預測的技巧。本論文中, 我們建構了一個

    新的神經網路模式--動態徑向基底函數 (dynamical radial basis

    function) 網路 (DRBF網路) , 並且用這種模式的神經網路作為「函數近

    似子」(function approximator) 去處理預測上的問題。另外我們也設計

    幾種不同的學習演算法以測試DRBF網路的功能。

    The forecasting technique is important for many researches and

    applications. In this paper, we shall construct a new model of

    neural networks -- the dynamical radial basis function (DRBF)

    networks and use the DRBF networks as "function approximators"

    to solve some forecasting problems. Different learning

    algorithms are used to test the capability of DRBF networks.

    Abstract i
    List of Figures iv
    List of Tables v
    Section 1 introduction 1
    1.1 Background.................................................................................................................1
    1.2 DRBF Networks...........................................................................................................2
    1.3 The Structure of This Paper.........................................................................................3

    Section 2 Previous Research 4
    2.1 The Approximation of Functions.................................................................................4
    2.2 Feedforward Networks.................................................................................................5
    2.3 Back Propagation Networks.........................................................................................6
    2.4 Forecasting....................................................................................................................7

    Section 3 Dynamical Radial Basis Function Networks 9
    3.1 RBF Networks..............................................................................................................9
    3.2 DRBF Networks.........................................................................................................12
    3.3 Changing Widths........................................................................................................14

    Section 4 Experiments 16
    4.1 f(x)=4x(1-x)................................................................................................................17
    4.2 f(x)=sin(-πx).............................................................................................................19
    4.3 AR(1)..........................................................................................................................21
    4.4 MA(1).........................................................................................................................23
    4.5 Sunspots......................................................................................................................25
    4.6 Discussion...................................................................................................................27

    Section 5 Conclusion 28
    Reference 29

    [1] Bishop, C.(1991). Improving the generalization properties of radial basis function neural networks. Neural Computation, 3, 579-589.
    [2] Broomhead, D. S., & Lowe, D. (1988). Multivariable functional interpolation and adaptive networks. Complex Systems, 2, 321-355.
    [3] Chen, S., Cowan, C. F. N., & Grant, P. M. (1991). Orthogonal least suares learning algorithm for radial basis function networks. IEEE Transcations on Neural Networks, 2, 302-309

    [4] Friedberg, S. H., Insel, A. J., & Spence, L. E. (1989). Linear Algebra. Englewood Cliffs, N.j.: Prentice-Hall, Inc.
    [5] Hartman, E. J., Keeler, J. D., & Kowalski, J. M. (1990). Layered neural networks with Gaussian Hidden units as universal approximations. Neural Computation, 2, 210-219.
    [6] Jones, R. D., Lee, Y. C., Barnes, C. W., Flake, G. W., Lee, K., Lewis, P.S., & Qian, S. (1990). Function approximation and time series prediction with neural networks. Proceedings of International Joint Confernence on Neural Networks, 1, 649-665.
    [7] Lapedes, A. S., & Farber, R. M. (1987). Nonlinear signal processing using neural networks: prediction and system modeling. Technical Report. Los Alamos National Laboratory, Los Alamos, New Mexico.
    [8] May, R. M. And Sugihara, G. (1990). Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series. Nature, 344, 734-741.
    [9] Moody J., & Darken, C. J. (1989). Fast learning in networks of locally tuned processing units. Neural Computation, 1, 281-294.
    [10] Musavi, M. T., Ahmed, W., Chan, K. H., Faris, K. B., & Hummels, D. M. (1992). On the training of radial basis function classifiers, Neural Networks. 5,595-603.
    [11] Park, J., & Sandberg, I. W. (1991). Universal approximation using radial-basis-function networks. Neural Computation, 3, 246-257.
    [12] Qian, S., Lee, Y. C., Jones, R. D., Barnes, C. W., & Lee, K. (1990). Function approximation with an orthogonal basis net. Technical Report. Los Alamos National Laboratory, Los Alamos, New Mexico.
    [13] Rasband, S. N. (1990). Chaotic Dynamics of Nonlinear System. New York: John Wiley & Sons, Inc.
    [14] Rice, J. R. (1964). The Approximation of Functions. Reading, Mass: Addison-Wesley Pubblish Company, Inc.
    [15] Rumelhart, D. E., & McClelland, J. L. (1986). Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Cambridge, Mass.: MIT Press.
    [16] Weigend, A. S., Huberman, B. A., & Rumelhart, D. E. (1990). Predicting the future: a connectionist approach. International Journal of Neural Systems, 1, 193-209.

    無法下載圖示 (限達賢圖書館四樓資訊教室A單機使用)
    QR CODE
    :::