Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/6532
標題: 適應性自我組織映射與應用
Adaptive Self-Organizing Map and Its Applications
作者: 李東霖
Li, Dong-Lin
關鍵字: Self-organizing map;自我組織映射;Data clustering;資料分群
出版社: 電機工程學系所
引用: [1] S. C. Ahalt, A. K. Arishnamurty, P. Chen, and D. E. Melton, “Competitive learning algorithms for vector quantization,” Neural Networks, vol. 3, pp. 277–291, 1990. [2] N. B. Karayiannis, “A methodology for constructing fuzzy algorithms for learning vector quantization,” IEEE Trans. Neural Networks, vol. 8, pp. 505–518, May 1997. [3] N. B. Karayiannis and P.-I. Pai, “Fuzzy algorithms for learning vector quantization,” IEEE Trans. Neural Networks, vol. 7, pp. 1196–1211, Sept. 1996. [4] I. Pitas, C.Kotropoulos, N. Nikolaidis, R.Yang, and M. Gabbouj, “Order statistics learning vector quantizer,” IEEE Trans. Image Processing, vol. 5, pp. 1048–1053, June 1996. [5] E. Yair, K. Zeger, and A. Gersho, “Competitve leaning and soft competition for vector quantization design,” IEEE Trans. Signal Processing , vol. 40, pp. 294–309, Feb. 1992. [6] C. Zhu and L.-M. Po, “Minimax partial distortion competitive learning for optimal codebook design,” IEEE Trans. Image Processing, vol. 7, pp. 1400–1409, Oct. 1998. [7] A. Gersho and R. M. Gray, Vector Quantization and Signal Compression. Norwell, MA: Kluwer, 1992. [8] A. K. Jain and R. C. Dubes, Algorithms for Clustering Data. Englewood Cliffs, NJ: Prentice-Hall, 1988. [9] Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Trans. Communications, vol. COM-28, pp. 84–94, Jan. 1980. [10] T. Kohonen, Self-Organization and Associative Memory. New York: Springer-Verlag, 1984, vol. 8, Springer Ser. Inform. Sci.. [11] D. Desieno, “Adding a conscience to competitive learning,” in Proc. IEEE Int. Conf. Neural Networks, vol. I, New York, July 1988, pp. 117–124. [12] D. I. Choi and S. H. Park, “Self-creating and organizing neural network, ” IEEE Trans. Neural Networks, vol. 5, pp. 561–575, July 1994. [13] B. Fritzke, “Growing cell structures a self-organizing neural networks for unsupervised and supvised learning,” Neural Networks, vol. 7, no. 9, pp. 1441–1460, 1994. [14] J.-H. Wang and W.-D. Sun, “Online learning vector quantization: A harmonic competition approach based on conservation network,” IEEE Trans. Syst., Man, Cybern.—Part B: Cybern., vol. 29, pp. 642–653, Oct. 1999. [15] Huilin Xiong; Swamy, M.N.S.; Ahmad, M.O.; Irwin King;” Branching competitive learning Network:A novel self-creating model,” IEEE Trans, Neural Networks, Vol. 15, pp.417 – 429, March 2004 [16] 蘇木春,張孝德,「機器學習:類神經網路、模糊系統以及基因演算法則」,全華科技圖書股份有限公司,民國90 年7 月。 [17] 葉怡成,「類神經網路模式應用與實作」,儒林圖書有限公司,民國91 年3 月 [18] T. Kohonen, “Self-Organizing Maps,” 3nded., New York, 2001. [19] M. A. Kraaijveld, J. Mao, and A. K. Jain, “A Nonlinear Projection Method Based on Kohonen’s Topology Preserving Maps,” IEEE Trans. On Neural Networks, Vol.6, May 1995, pp. 548–559. [20] 林昇甫,洪成安,「神經網路入門與圖樣辨視」,全華科技圖書股份有限公司,民國85年5月二版。 [21] Forgy, E., “Cluster analysis of multivariate data: Efficiency versus interpretability of classifications,” Biometrics, Vol.21, pp.768, 1965. [22] T. Kohonen, Ed., “Self-Organizing Maps. Berlin, Germany: Springer - Verlag,” 1995. [23] J.C. Bezdek. “Pattern Recognition with Fuzzy Objective Function Algorithms.”New York. Kluwer Academic Norwell, 1981. [24] Weiming Hu; Xie, D.; Tieniu Tan; Maybank, S.“Learning activity patterns using fuzzy self-organizing neural network,” IEEE Trans. Systems, Man and Cybernetics, Part B, Vol. 34, June 2004, pp. 1618 – 1626.
摘要: 
自我組織映射架構的類神經網路是資料分群中常被用使用的一種方法。本論文提出了一種新的改良式自我組織映射演算法。它的神經元鄰近關係不像一般自我組織映射定義在二維的拓撲平面上,而是建立在以立方體呈現的三維拓撲空間。為了避免網路中死點的產生,在其競爭學習的過程中,其網路結構也會隨時間的不同去動態調整每個神經元之間的鍵結情況。最後再結合自我建立模組使其網路結構在競爭學習的過程中能夠自動調整網路大小,而更適應性的處理各種特殊的資料分佈形態。

Self-organizing neural network is one of the methods frequently used in data clustering. In this thesis, we present a new method to improve the self-organizing map algorithm. Instead of the 2-D neighborhood topology in the conventional self-organizing map, a 3-D 6-neighbor topology is adopted in our approach. To avoid the dead (non-functional) neurons and to represent the training data more effectively, the number of neurons and the links between the neurons will be adjusted automatically during the process of the competitive learning by using a self-constructing model.
URI: http://hdl.handle.net/11455/6532
其他識別: U0005-2007200616333900
Appears in Collections:電機工程學系所

Show full item record
 
TAIR Related Article

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.