Download file (3.05MB)
Download as zip (2.63MB)

コレクション

引用

説明:

Reservoir computing is a promising approach to implementing high-performance artificial intelligence that can process input data at lower computational costs than conventional artificial neural networks. Although reservoir computing enables real-time processing of input time-series data on artificial intelligence mounted on terminal devices, few physical devices are capable of high-speed operation for real-time processing. In this study, we introduce spin wave interference with a stepped input method to reduce the operating time of the physical reservoir, and second-order nonlinear equation task and second-order nonlinear autoregressive mean averaging, which are well-known benchmark tasks, were carried out to evaluate the operating speed and prediction accuracy of said physical reservoir. The demonstrated reservoir device operates at the shortest operating time of 13 ms/5000-time steps, compared to other compact reservoir devices, even though its performance is higher than or comparable to such physical reservoirs. This study is a stepping stone toward realizing an artificial intelligence device capable of real-time processing on terminal devices.

権利情報:

• Creative Commons BY Attribution 4.0 International
  

キーワード: Reservoir computing , Spin wave inteference, Neuromorphic computing

刊行年月日: 2024-06-01

出版者: IOP Publishing

掲載誌:

• Neuromorphic Computing and Engineering (ISSN: 26344386) vol. 4 issue. 2 024015

研究助成金:

• Japan Society for the Promotion of Science JP21J21982
• Innovative Science and Technology Initiative for Security Grant JPJ004596
• Ministry of Education, Culture, Sports, Science and Technology JPMXP1223NM5072
• JSPS
• National Institute for Materials Science

原稿種別: 出版者版 (Version of record)

MDR DOI:

公開URL: https://doi.org/10.1088/2634-4386/ad561a

関連資料:

その他の識別子:

連絡先:

更新時刻: 2024-08-05 12:30:22 +0900

MDRでの公開時刻: 2024-08-05 12:30:22 +0900