Presentation 2020-01-24
Electronic implementation of a physical reservoir composed of discrete semiconductor devices
Shunya Suzuki, Koyo Minamikawa, Megumi Akai-Kasaya, Tetuya Asai,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Reservoir computing is a recurrent neural network that has loop structures. The main difference from typical recurrent neural networks is that only the output weight is determined by learning. The structure of the middle layer (called the reservoir) is initially given randomly and is not changed. Therefore, it is considered that the reservoir has a high affinity for physical dynamics, and its implementation using various physical systems, such as optics, spin, elastic body, and memristor is studied. In this study, we propose a high-accuracy reservoir with a simple structure using electronic circuits as a new physical reservoir.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reservoir Computing / Electronic circuit / Discrete time / Time series prediction
Paper # NLP2019-99
Date of Issue 2020-01-16 (NLP)

Conference Information
Committee NLP / NC
Conference Date 2020/1/23(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Miyakojima Marine Terminal
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Hiroaki Kurokawa(Tokyo Univ. of Tech.) / Hayaru Shouno(UEC)
Vice Chair Kiyohisa Natsume(Kyushu Inst. of Tech.) / Kazuyuki Samejima(Tamagawa Univ)
Secretary Kiyohisa Natsume(Nippon Inst. of Tech.) / Kazuyuki Samejima(Kyushu Inst. of Tech.)
Assistant Yutaka Shimada(Saitama Univ.) / Toshikaza Samura(Yamaguchi Univ.) / Takashi Shinozaki(NICT) / Ken Takiyama(TUAT)

Paper Information
Registration To Technical Committee on Nonlinear Problems / Technical Committee on Neurocomputing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Electronic implementation of a physical reservoir composed of discrete semiconductor devices
Sub Title (in English)
Keyword(1) Reservoir Computing
Keyword(2) Electronic circuit
Keyword(3) Discrete time
Keyword(4) Time series prediction
1st Author's Name Shunya Suzuki
1st Author's Affiliation Hokkaido University(Hokkaido Univ.)
2nd Author's Name Koyo Minamikawa
2nd Author's Affiliation Hokkaido University(Hokkaido Univ.)
3rd Author's Name Megumi Akai-Kasaya
3rd Author's Affiliation Hokkaido University(Hokkaido Univ.)
4th Author's Name Tetuya Asai
4th Author's Affiliation Hokkaido University(Hokkaido Univ.)
Date 2020-01-24
Paper # NLP2019-99
Volume (vol) vol.119
Number (no) NLP-381
Page pp.pp.73-78(NLP),
#Pages 6
Date of Issue 2020-01-16 (NLP)