Constructing hysteretic memory in neural networks
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
609 | en_US |
dc.citation.issue |
4 | en_US |
dc.citation.spage |
601 | en_US |
dc.citation.volume |
30 | en_US |
dc.citation.woscount |
40 | |
dc.contributor.author |
Wei, JD | en_US |
dc.contributor.author |
Sun, CT | en_US |
dc.contributor.department |
資訊工程學系 | zh_TW |
dc.contributor.department |
Department of Computer Science | en_US |
dc.date.accessioned |
2014-12-08T15:44:58Z | |
dc.date.available |
2014-12-08T15:44:58Z | |
dc.date.issued |
2000-08-01 | en_US |
dc.description.abstract |
Hysteresis is a unique type of dynamic, which contains an important property, rate-independent memory. In addition to other memory-related studies such as time delay neural networks, recurrent networks, and reinforcement learning, rate-independent memory deserves further attention owing to its potential applications. In this work, we attempt to define hysteretic memory (rate-independent memory) and examine whether or not it could be modeled in neural networks. Our analysis results demonstrate that other memory-related mechanisms are not hysteresis systems. A novel neural cell, referred to herein as the propulsive neural unit, is then proposed. The proposed cell is based on a notion related the submemory pool, which accumulates the stimulus and ultimately assists neural networks to achieve model hysteresis. In addition to training by backpropagation, a combination of such cells can simulate given hysteresis trajectories. | en_US |
dc.identifier.doi |
10.1109/3477.865179 | en_US |
dc.identifier.issn |
1083-4419 | en_US |
dc.identifier.journal |
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1109/3477.865179 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/30354 | |
dc.identifier.wosnumber |
WOS:000089118000012 | |
dc.language.iso |
en_US | en_US |
dc.subject |
hysteresis | en_US |
dc.subject |
hysteretic memory | en_US |
dc.subject |
rate independence | en_US |
dc.subject |
recurrent network | en_US |
dc.subject |
reinforcement learning | en_US |
dc.subject |
time delay neural network | en_US |
dc.title |
Constructing hysteretic memory in neural networks | en_US |
dc.type |
Article | en_US |
檔案
- 000089118000012.pdf (257.1 KB, Adobe PDF)
所屬典藏: 期刊論文
引用此條目
Wei, J., & Sun, C. (2000). Constructing hysteretic memory in neural networks. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 30(4), 601–609. https://doi.org/10.1109/3477.865179
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/30354