請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/24570
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 劉長遠 | |
dc.contributor.author | Jiun-Wei Liou | en |
dc.contributor.author | 劉俊緯 | zh_TW |
dc.date.accessioned | 2021-06-08T05:31:24Z | - |
dc.date.copyright | 2005-07-05 | |
dc.date.issued | 2005 | |
dc.date.submitted | 2005-06-28 | |
dc.identifier.citation | [1] Bruck, J., “On the convergence properties of the Hopfield model,” Proc. IEEE, vol. 78,
pp.1579-1585, Oct. 1990. [2] Hopfield, J. J., “Neural networks and physical systems with emergent collective computational abilities,” Proc. Nat. Academy Sci., vol. 79, pp. 2554-2558, Apr. 1982. [3] Li, J., Michael, A. N., and Porod, W., “Qualitative analysis and synthesis of a class of neural networks,” IEEE Trans. Circuits System, vol. 35, pp. 976-986, Aug. 1988. [4] Lillo, W. E., Miller, D. C., and Zak, S. H., “Synthesis of brain-state-in-a-box(BSB) based on associative memory,” IEEE Trans. Neural Networks, vol. 5, no. 5, pp. 730-737, Sep. 1994. [5] Liou, C. Y., and Yuan, S. K., “Error tolerant associative memory,” Biological Cybernetics, vol. 81, pp.331-342, 1999. [6] Personnaz, L., Guyon, I., and Drefus, G., “Information storage and retrieval in spin-glass like neural networks,” J. Phys. Lett., vol. 46, pp. 359-366, Apr. 1985. [7] Tao, Q. and Fang, T., “The neural network based on constraint domain and its applications” (in Chinese), Chinese Artificial Intell. Pattern Recognition, vol. 11, no. 4, pp. 472-478, 1998. [8] Tao, Q., Fang, T., and Qiao, H.,“A novel continuous-time neural network for realizing associative memory,” IEEE Trans. Neural Networks, vol. 12, no.2, pp. 418-423, Mar. 2001. [9] Tao, Q., Cao, J., Sun, D., “A simple and high performance neural network for quadratic programming problems”, Applied Mathematics and Computation, vol.124, pp. 251—260, 2001. [10] Tao, Q., Cao, J., and Liu, X., “The BSB neural network in the convex body spanned by the prototype patterns for associative memory,” Applied Mathematics and Computation, vol. 132, pp. 175-187, 2002. [11] Xia, Y., “A new neural network for solving linear and quadratic programming problems,” IEEE Trans. Neural Networks, vol. 7, no. 6, pp. 1544-1547, Nov. 1996. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/24570 | - |
dc.description.abstract | 本文討論並比較三種聯想記憶模式,分別是陶卿等所著的模式[8],etAM(容錯聯想記憶),和mECR(錯誤更正規則)。在本文中整理分析這三種記憶模式,並依照這三種模式對於所有的輸入可能的收斂性作比較。
本文取材自國科會計畫(NSC 93-2213-E-002-081)與類神經網路課程(922 U1180)講義討論三個聯想記憶結構,其中一個結構為陶卿等所著[8],另二結構請參考作品[5]。陶的程式由助理吳泰輝同學提供,[5]的程式取材自講義。作者自 94 年 3 月下旬開始比較這三個記憶結構,並將結果整理記載成文。 | zh_TW |
dc.description.abstract | This paper discusses three associative memory models. The three models are Tao's AM, etAM and mECR. Tao's AM is based on projection on a closed convex set spanned by patterns. etAM and mECR are based on tuning hyperplanes to get the desired error tolerance. The three models are analyzed, and then compared based on the convergence of all possible binary inputs. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T05:31:24Z (GMT). No. of bitstreams: 1 ntu-94-R92922001-1.pdf: 767439 bytes, checksum: 162dace899d8143ecd023b3c51ab2678 (MD5) Previous issue date: 2005 | en |
dc.description.tableofcontents | Contents
1 Introduction 1 2 Theorem 4 2.1 Tao’s AM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 etAM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.3 mECR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3 Analysis and Comparison 11 3.1 Tao’s AM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2 etAM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.3 mECR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22 3.4 Conparison among AMs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.5 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 4 Conclusion 37 4.1 Future works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 A The large tables for comparison between AMs 38 i | |
dc.language.iso | zh-TW | |
dc.title | 兩種聯想記憶模式之研究 | zh_TW |
dc.title | A Comprehensive Survey on Two Associative Memory Models | en |
dc.type | Thesis | |
dc.date.schoolyear | 93-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 呂育道,林智仁,傅心家,吳建銘 | |
dc.subject.keyword | 類神經網路,聯想記憶, | zh_TW |
dc.subject.keyword | Neural network,Hopfield model,associative memory,recurrent network, | en |
dc.relation.page | 49 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2005-06-28 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-94-1.pdf 目前未授權公開取用 | 749.45 kB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。