Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/108119
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 曾睿彬 | zh_TW |
dc.contributor.advisor | Tseng, Jui-Pin | en_US |
dc.contributor.author | 陳冠瑋 | zh_TW |
dc.contributor.author | Chen, Guan-Wei | en_US |
dc.creator | 陳冠瑋 | zh_TW |
dc.creator | Chen, Guan-Wei | en_US |
dc.date | 2017 | en_US |
dc.date.accessioned | 2017-04-05T07:36:48Z | - |
dc.date.available | 2017-04-05T07:36:48Z | - |
dc.date.issued | 2017-04-05T07:36:48Z | - |
dc.identifier | G0103751015 | en_US |
dc.identifier.uri | http://nccur.lib.nccu.edu.tw/handle/140.119/108119 | - |
dc.description | 碩士 | zh_TW |
dc.description | 國立政治大學 | zh_TW |
dc.description | 應用數學系 | zh_TW |
dc.description | 103751015 | zh_TW |
dc.description.abstract | 這篇論文研究具多重穩定性之時間延遲型霍普菲爾神經網路。我們以兩個神經元所組成的神經網路來表現我們的想法。運用方程式的幾何結構,我們可推導出各種使網路具有不同數量固定點的條件,我們可以進一步建立網路系統的全局收斂性。 | zh_TW |
dc.description.tableofcontents | 中文摘要 iii\nAbstract iv\nContents v\nList of figures vii\nList of tables ix\n1 Introduction 1\n2 Literature review and study motivation 3\n2.1 General cases 3\n2.2 Other cases for n = 2 6\n3 Main results 10\n3.1 Exact number of equilibria for case 1 10\n3.1.1 K2(p˜2; A1) > 0 10\n3.1.2 K2(p˜2; C1) < 0 16 \n3.1.3 K2(p˜2; A1) < 0 < K2(p˜2; B1) 24 \n3.1.4 K2(p˜2; B1) < 0 < K2(p˜2; C1) 31 \n3.2 Exact number of equilibria for case 2 39\n3.2.1 K2(p˜2; A1) > 0 41\n3.2.2 K2(p˜2; A1) < 0 < K2(p˜2; S1) and K1(q˜1; SS1 ) > 0 51 \n3.2.3 K2(p˜2; S1) < 0 and K1(q˜1; AS1 ) > 0 57 \n3.3 Convergence of dynamics for case 1 under conditions K2(p˜2; A1) > 0 69\n4 Numerical examples 78\nReferences 98 | zh_TW |
dc.format.extent | 3572277 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.source.uri | http://thesis.lib.nccu.edu.tw/record/#G0103751015 | en_US |
dc.subject | 神經網路 | zh_TW |
dc.subject | 多重穩定性 | zh_TW |
dc.subject | 時間延遲 | zh_TW |
dc.subject | 收斂性 | zh_TW |
dc.title | 具時間延遲之霍普菲爾神經網路的多重穩定性 | zh_TW |
dc.title | Multistability in Hopfield-type neural networks with delays | en_US |
dc.type | thesis | en_US |
dc.relation.reference | [1] Nikola Burić and Dragana Todorović. Dynamics of fitzhugh-nagumo excitable systems with delayed coupling. Phys. Rev. E, 67:066222, Jun 2003.\n[2] Sue Ann Campbell, R. Edwards, and P. van den Driessche. Delayed coupling between two neural network loops. SIAM J. Appl. Math., 65(1):316–335, 2004.\n[3] Chang-Yuan Cheng, Kuang-Hui Lin, Chih-Wen Shih, and Jui-Pin Tseng. Multistability for delayed neural networks via sequential contracting. IEEE Trans. Neural Netw. Learn. Syst., 26(12):3109–3122, 2015.\n[4] Michael A. Cohen and Stephen Grossberg. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. Systems Man Cybernet., 13(5):815–826, 1983.\n[5] Jennifer Foss, André Longtin, Boualem Mensour, and John Milton. Multistability and de- layed recurrent loops. Phys. Rev. Lett., 76:708–711, Jan 1996.\n[6] J. J. Hopfield. Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences, 81:3088– 3092, 1984.\n[7] Xiaoxin Liao and Jun Wang. Global dissipativity of continuous-time recurrent neural net- works with time delay. Phys. Rev. E (3), 68(1):016118, 7, 2003.\n[8] Jui-Pin Tseng. Global asymptotic dynamics of a class of nonlinearly coupled neural net- works with delays. Discrete Contin. Dyn. Syst., 33(10):4693–4729, 2013.\n[9] Jianhong Wu. Introduction to neural dynamics and signal transmission delay, volume 6 of de Gruyter Series in Nonlinear Analysis and Applications. Walter de Gruyter & Co., Berlin, 2001. | zh_TW |
item.fulltext | With Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_46ec | - |
item.cerifentitytype | Publications | - |
item.grantfulltext | restricted | - |
item.openairetype | thesis | - |
Appears in Collections: | 學位論文 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
101501.pdf | 3.49 MB | Adobe PDF2 | View/Open |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.