我們運用蜂巢式類神經網路(Cellular neural network)於震測水平連接(Seismic Horizon Linking)及圖型識別(Pattern Recognition).在震測水平連接方面,我們經由建構數種不同的條件,以其形成的能量方程式和蜂巢式類神經網路之能量方程式做比較,完成網路訓練的過程(Training Process),然後我們利用這完成訓練的網路來處理震測水平連接的問題.在圖型識別的方面,我們將蜂巢式類神經網路設計成聯想記憶體(Associative Memory),然後再用它來辨識圖型.我們針對二值的圖型(Bipolar pattern)做分類辨識的運用.在我們的實驗中,不論震測水平連接或圖型識別,均有良好的實驗結果.

目 錄
中 文 摘 要…..…………………………………………………….…..i
英 文 摘 要……………..………………………………………….….ii
誌 謝…………………………..……………………………………….iii
目 錄…………………………………………………………………...iv
表 目 錄……………………………………………………………….vi
圖 目 錄……………………………………………………………...viii
第 一 章 概 論….……………………………………………1
1.1 動機………………………………………………1
1.2 論文架構..………………………………………..2
第 二 章 蜂巢式類神經網路於震測水平之連接…………..3
2.1 蜂巢式類神經網路………………….……….….3
2.2 運動方程式與能量之關係……..……………….6
2.3 震測水平連接………………………….………..9
2.4 例子…………………………………………….26
2.5 實驗…………………………………………….32
第 三 章 蜂巢式類神經網路於圖型之識別….…………..46
3.1 聯想記憶體……………………………………..46
3.2 運用聯想記憶體做圖型辨識…………………..63
3.3 例子……………………………………………..65
3.4 實驗……………………………………………..73
第 四 章 結論與討論……………..………………..……….. 82
REFRENCES…………………………………………………………………. 83

REFERENCES
[1] L. O. Chua and Lin Yang, “Cellular Neural Networks: Theory,” IEEE Trans. on CAS, vol. 35 no. 10, pp.1257-1272, 1988.
[2] M. Forti and A. Tesi, “ New conditions for global stability of neural networks with application to linear and quadratic programming problems,” IEEE Trans. Cir. Syst. I, vol. 42, pp. 354-366, July, 1995.
[3] L. O. Chua and Lin Yang, “Cellular Neural Networks: Applications,” IEEE Trans. on CAS, vol.35, no.10, pp. 1273-1290, 1988.
[4] L. O. Chua, “Dynamic nonlinear networks: State of the art,” IEEE Trans. Circuits Syst., pp.1059-1087, 1980.
[5] Kou-Yuan Huang, “Neural network for seismic horizon picking,” IEEE World Congress on Computational Intelligence, The 1998 IEEE International Joint Conference on. Volume: 3, 1998.
[6] J. J. Hopfield, and T. W. Tank, “Neural computation of decisions in optimization problems,” Biological Cybernetics, 52, pp. 141-152, 1985.
[7] Kou-Yuan Huang, W. R. I. Chang & H. T. Yen, “Self Organising Neural network for picking Seismic horizons,” Proc. of Annual SEG Meeting, pp. 313-315, San Francisco, 1990.
[8] Kou-Yuan Huang, “Branch and bound search for automatic linking process of seismic horizons,” Pattern Recognition, Volume 23, No. 6, pp. 657-667, 1990
[9] Kou-Yuan Huang, “Hopfield model of neural networks for detection of bright-spot,” presented at the 59 th Ann. Internat. Mtg., Soc. Explor. Geophys., 1989.
[10] Kou-Yuan Huang, “Seismic horizon picking using a Hopfield network,” invited, in Geophysical Applications of Artificial Neural Networks and Fuzzy Logic, edited by William Sandham and Miles Leggett, Kluwer Academic Publishers, 2000.
[11] M. Brucoli, L. Carnimeo, and G. Grassi, “Associative memories design using discrete-time second-order neural networks with local interconnections,” IEEE Trans. Cir. Syst. I, vol. 44, pp. 153-158, Feb, 1997.
[12] M. Brucoli, L. Carnimeo, and G. Grassi, “A global approach to the design of discrete-time cellular neural networks for associative memories,” Int. J. Circuit Theory Appl., vol. 24, no. 4, pp. 489-510, 1996.
[13] R. Perfetti, “ Dual-mode space-varying self-designing cellular neural networks for associative memories,” IEEE Trans. Cir. Syst. I, vol. 46, pp. 1281-1285, Oct, 1999.
[14] D. Liu and A. N. Michel, “ Sparsely interconnected neural networks for associative memories with applications to cellular neural networks,” IEEE Trans. Cir. Syst. II, vol. 41, pp. 295-307, April, 1994.
[15] R. Perfetti, “ Frequency domain stability criteria for cellular neural networks, ” Int. J. Circuit Theory Appl., vol. 25, no. 1, pp. 55-68, 1997.
[16] M. P. Joy and V. Tavsanoglu, “ Circulant matrices and the stability of a class of CNNs, ” Int. J. Circuit Theory Appl., vol. 24, no. 1, pp. 7-13, 1996.
[17] C. Guzelis and L. O. Chua, “Stability analysis of generalized cellular neural networks, ” Int. J. Circuit Theory Appl., vol. 21, no. 1, pp. 1-33, 1993.
[18] G. Grassi, “ A new approach to design cellular neural networks for associative memories,” IEEE Trans. Cir. Syst. I, vol. 44, pp. 835-838, Sept, 1997.
[19] M.Forti and A. Tesi, “New conditions for global stability of neural networks with application to linear and quadratic programming problems,” IEEE Trans. Cir. Syst. I, vol. 42, pp. 354-366, July, 1995.
[20] M. Brucoli, L. Carnimeo, and G. Grassi, “ Discrete-time cellular neural networks for associative memories with learning and forgetting capabilities,” IEEE Trans. Cir. Syst. I, vol. 42, pp. 396-399, July, 1995.
[21] A. Ben-Israel and T. N. E. Greville, Generalized Inverses: Theory and Applications. New Yoke: Wiley, 1974.
[22] D. Liu and A. N. Michel, “ Cellular neural networks for associative memories,” IEEE Trans. Cir. Syst. II, vol. 40, pp. 119-121, 1993.
[23] C. Peterson and J. R. Anderson, “A mean field theory learning algorithm for neural network,” Complex Systems, vol.1, no.5, pp. 995-1019, 1987.
[24] S. Tan, J. Hao, and J. Vandewalle, “Cellular Neural Networks as a model of associative memories,” in Proc. 1st Int. Workshop Cellular Neural Networks and Their Applications (CNNA`90), Budapest, Hungary, pp. 26-35, 1990.
[25] G. Martinelli and R. Perfetti,” Associative memory design using space-varying cellular neural networks,” in Proc. 2nd Int. Workshop on Cellular Neural Networks and Their Applications (CNNA`92), Munich, Germany, pp. 117-122, 1992.