article · Japanese Journal of Applied Physics · 2019
Reservoir computing with two-bit input task using dipole-coupled nanomagnet array
Hikaru Nomura, Kazuki Tsujimoto, Minori Goto, Naoki Samura, Ryoichi Nakatani, Yoshishige Suzuki
Cited by 13Abstract and details only
Abstract
Abstract Reservoir computing (RC), which utilizes physical phenomena, is a candidate for low energy consumption recurrent neural networks. Recently, we proposed RC which uses a dipole-coupled nanomagnet array as a reservoir, which applies the direction of the static magnetic moment of each nanomagnet as a node state in the array. It is possible to learn binary tasks with one-bit input data using this reservoir. Moreover, more complex tasks such as motion detection utilize multi-bit input data. This study simulates a two-bit binary input RC by employing the dipole coupled nanomagnet array as a reservoir. We apply a binary task with two-bit input data, which requires a memory capacity and non-linear computing capability of the reservoir. Due to the simulations with a macrospin model at a temperature of 0 K, this RC was able to learn these binary tasks by utilizing 24 nanomagnets.
Cite this paper
Nomura, H., Tsujimoto, K., Goto, M., Samura, N., Nakatani, R., & Suzuki, Y. (2019). Reservoir computing with two-bit input task using dipole-coupled nanomagnet array. Japanese Journal of Applied Physics, 59(SE), SEEG02. https://doi.org/10.7567/1347-4065/ab4f0f
Nomura, Hikaru, et al. “Reservoir computing with two-bit input task using dipole-coupled nanomagnet array.” Japanese Journal of Applied Physics, vol. 59, no. SE, 2019, p. SEEG02, https://doi.org/10.7567/1347-4065/ab4f0f.
Nomura, Hikaru, Kazuki Tsujimoto, Minori Goto, Naoki Samura, Ryoichi Nakatani, and Yoshishige Suzuki. 2019. “Reservoir computing with two-bit input task using dipole-coupled nanomagnet array.” Japanese Journal of Applied Physics 59 (SE): SEEG02. https://doi.org/10.7567/1347-4065/ab4f0f.
Nomura, H. et al. (2019) ‘Reservoir computing with two-bit input task using dipole-coupled nanomagnet array’, Japanese Journal of Applied Physics, 59(SE), p. SEEG02. Available at: https://doi.org/10.7567/1347-4065/ab4f0f.
@article{nomura2019reservoir,
title = {{Reservoir computing with two-bit input task using dipole-coupled nanomagnet array}},
author = {Nomura, Hikaru and Tsujimoto, Kazuki and Goto, Minori and Samura, Naoki and Nakatani, Ryoichi and Suzuki, Yoshishige},
journal = {Japanese Journal of Applied Physics},
volume = {59},
number = {SE},
pages = {SEEG02},
year = {2019},
doi = {10.7567/1347-4065/ab4f0f}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.