Please use this identifier to cite or link to this item:
https://ah.lib.nccu.edu.tw/handle/140.119/129986
DC Field | Value | Language |
---|---|---|
dc.contributor | 應數系 | |
dc.creator | 班榮超 | |
dc.creator | Ban, Jung-Chao | |
dc.creator | Chang, Chih-Hung | |
dc.date | 2016-03 | |
dc.date.accessioned | 2020-05-27T01:02:17Z | - |
dc.date.available | 2020-05-27T01:02:17Z | - |
dc.date.issued | 2020-05-27T01:02:17Z | - |
dc.identifier.uri | http://nccur.lib.nccu.edu.tw/handle/140.119/129986 | - |
dc.description.abstract | This paper studies the initial value problem of multi-layer cellular neural networks. We demonstrate that the mosaic solutions of such system is topologically conjugated to a new class in symbolic dynamical systems called the path set (Abram and Lagarias in Adv Appl Math 56:109–134, 2014). The topological entropies of the solution, output, and hidden spaces of a multi-layer cellular neural network with initial condition are formulated explicitly. Also, a sufficient condition for whether the mosaic solution space of a multi-layer cellular neural network is independent of initial conditions is addressed. Furthermore, two spaces exhibit identical topological entropy if and only if they are finitely equivalent. | |
dc.format.extent | 1390467 bytes | - |
dc.format.mimetype | application/pdf | - |
dc.relation | Journal of Dynamics and Differential Equations, Vol.28, No.1, pp.69-92 | |
dc.subject | Initial value problem ; Cellular neural networks ; Sofic shift ; Path set | |
dc.title | Solution Structure of Multi-layer Neural Networks with Initial Condition | |
dc.type | article | |
dc.identifier.doi | 10.1007/s10884-015-9471-9 | |
dc.doi.uri | https://doi.org/10.1007/s10884-015-9471-9 | |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.openairetype | article | - |
item.grantfulltext | restricted | - |
item.cerifentitytype | Publications | - |
item.fulltext | With Fulltext | - |
Appears in Collections: | 期刊論文 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.