完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.author | Lee, Donq-Liang | |
dc.date.accessioned | 2009-06-02T07:20:50Z | |
dc.date.accessioned | 2020-05-29T06:18:31Z | - |
dc.date.available | 2009-06-02T07:20:50Z | |
dc.date.available | 2020-05-29T06:18:31Z | - |
dc.date.issued | 2006-11-13T02:13:51Z | |
dc.date.submitted | 1999-12-20 | |
dc.identifier.uri | http://dspace.fcu.edu.tw/handle/2377/3157 | - |
dc.description.abstract | This paper presents a novel continuous-time Hopfield-type network which is suitable for temporal sequence recognition. Since it is difficult to implement a desired flow vector field distribution by using conventional matrix encoding scheme, a time-varying Hopfield model (TVHM) is proposed. The weight matrix of the TVHM is constructed in such a way that its auto-correlation and cross-correlation parts are encoded from two different sets of patterns. The proposed approach is different from the existing methods because neither synchronous dynamics nor interpolated training patterns are required. Experimental results are presented to illustrate the validity, recall capability, and the applications of the proposed model. | |
dc.description.sponsorship | 淡江大學, 台北縣 | |
dc.format.extent | 8p. | |
dc.format.extent | 816094 bytes | |
dc.format.mimetype | application/pdf | |
dc.language.iso | zh_TW | |
dc.relation.ispartofseries | 1999 NCS會議 | |
dc.subject | Hopfield networks | |
dc.subject | recalling dynamics | |
dc.subject | auto-correlation | |
dc.subject | cross-correlation | |
dc.subject | pattern sequence recognition | |
dc.subject.other | 類神經網路 | |
dc.title | Improved Hopfield Networks for Pattern Sequence Recognition | |
分類: | 1999年 NCS 全國計算機會議 |
文件中的檔案:
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
ce07ncs001999000105.pdf | 796.97 kB | Adobe PDF | 檢視/開啟 |
在 DSpace 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。