Multistability in recurrent neural networks
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
1320 | en_US |
dc.citation.issue |
4 | en_US |
dc.citation.spage |
1301 | en_US |
dc.citation.volume |
66 | en_US |
dc.citation.woscount |
69 | |
dc.contributor.author |
Cheng, CY | en_US |
dc.contributor.author |
Lin, KH | en_US |
dc.contributor.author |
Shih, CW | en_US |
dc.contributor.department |
應用數學系 | zh_TW |
dc.contributor.department |
Department of Applied Mathematics | en_US |
dc.date.accessioned |
2014-12-08T15:17:36Z | |
dc.date.available |
2014-12-08T15:17:36Z | |
dc.date.issued |
2006 | en_US |
dc.description.abstract |
Stable stationary solutions correspond to memory capacity in the application of associative memory for neural networks. In this presentation, existence of multiple stable stationary solutions for Hopfield-type neural networks with delay and without delay is investigated. Basins of attraction for these stationary solutions are also estimated. Such a scenario of dynamics is established through formulating parameter conditions based on a geometrical setting. The present theory is demonstrated by two numerical simulations on the Hopfield neural networks with delays. | en_US |
dc.identifier.doi |
10.1137/050632440 | en_US |
dc.identifier.issn |
0036-1399 | en_US |
dc.identifier.journal |
SIAM JOURNAL ON APPLIED MATHEMATICS | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1137/050632440 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/12771 | |
dc.identifier.wosnumber |
WOS:000238324300010 | |
dc.language.iso |
en_US | en_US |
dc.subject |
neural network | en_US |
dc.subject |
multistability | en_US |
dc.subject |
delay equations | en_US |
dc.title |
Multistability in recurrent neural networks | en_US |
dc.type |
Article | en_US |
檔案
- 000238324300010.pdf (646.1 KB, Adobe PDF)
所屬典藏: 期刊論文