WEKO3
アイテム
Noise-modulated neural networks for selectively functionalizing sub-networks by exploiting stochastic resonance
http://hdl.handle.net/10228/00009140
http://hdl.handle.net/10228/0000914090e8b535-58d9-48a3-a5e8-eb9459c017ca
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
10364395.pdf (1.2 MB)
|
|
| アイテムタイプ | 学術雑誌論文 = Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2023-03-27 | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Noise-modulated neural networks for selectively functionalizing sub-networks by exploiting stochastic resonance | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 著者 |
池本, 周平
× 池本, 周平
WEKO
30354
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | In the phenomenon of stochastic resonance, adding a certain level of nonzero noise to a nonlinear system reduces information loss. A previous study proposed a neural network consisting of thresholding functions that exploit stochastic resonance at run time and during training, with the aim of smooth mapping and backpropagation. Such a neural network can be rephrased as one that operates only when noise is added, i.e., one that is unable to smoothly map and train when noise is absent. Focusing on both explanations simultaneously, a neural network for which only a sub-network is activated selectively by adding noise locally on that sub-network is proposed in this paper. To this end, a new activation function is introduced. It exploits stochastic resonance and presents null output and derivative when no noise is added. Simple simulations confirm that the proposed neural network with the new activation function allows the sub-network to be functionalized selectively, and interpolations are investigated by imposing varying noise intensity on various regions of the network after sub-networks are trained separately. | |||||||||||||
| 言語 | en | |||||||||||||
| 書誌情報 |
en : Neurocomputing 巻 448, p. 1-9, 発行日 2021-03-26 |
|||||||||||||
| 出版社 | ||||||||||||||
| 出版者 | Elsevier | |||||||||||||
| DOI | ||||||||||||||
| 関連タイプ | isVersionOf | |||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.1016/j.neucom.2020.05.125 | |||||||||||||
| 日本十進分類法 | ||||||||||||||
| 主題Scheme | NDC | |||||||||||||
| 主題 | 549 | |||||||||||||
| NCID | ||||||||||||||
| 収録物識別子タイプ | NCID | |||||||||||||
| 収録物識別子 | AA10827402 | |||||||||||||
| ISSN | ||||||||||||||
| 収録物識別子タイプ | PISSN | |||||||||||||
| 収録物識別子 | 0925-2312 | |||||||||||||
| ISSN | ||||||||||||||
| 収録物識別子タイプ | EISSN | |||||||||||||
| 収録物識別子 | 1872-8286 | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報 | Copyright (c) 2021 Elsevier B.V. All rights reseved. | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Stochastic resonance | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Neural network | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Localized noise | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | AM | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||||||||||
| 査読の有無 | ||||||||||||||
| 値 | yes | |||||||||||||
| 研究者情報 | ||||||||||||||
| URL | https://hyokadb02.jimu.kyutech.ac.jp/html/100001226_ja.html | |||||||||||||
| 論文ID（連携） | ||||||||||||||
| 値 | 10364395 | |||||||||||||
| 連携ID | ||||||||||||||
| 値 | 8839 | |||||||||||||
