Presentation | 2021-08-17 Approximation of Non-Linear Function for Hardware Implementation of Echo-State-Network Amartuvshin Bayasgalan, Makoto Ikeda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Reservoir computing (RC) is a machine-learning algorithm that can learn complex temporal signals while presenting a fast and easy training procedure. For practical applications of RC in edge computing, its hardware implementation must be considered for its computational time and resource on which design of the neuron has a critical impact. This work presents different approximation methods of a non-linear function of echo-state-network to obtain the optimal design for the hardware implementation. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Echo-State-Network / Hyperbolic tangent / Non-Linear Function Approximation |
Paper # | SDM2021-32,ICD2021-3 |
Date of Issue | 2021-08-10 (SDM, ICD) |
Conference Information | |
Committee | SDM / ICD / ITE-IST |
---|---|
Conference Date | 2021/8/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Analog, Mixed Analog and Digital, RF, and Sensor Interface, Low Voltage/Low Power Techniques, Novel Devices/Circuits, and the Applications |
Chair | Hiroshige Hirano(TowerPartners Semiconductor) / Masafumi Takahashi(Kioxia) / AKITA Junichi(Kanazawa Univ.) |
Vice Chair | Shunichiro Ohmi(Tokyo Inst. of Tech.) / Makoto Ikeda(Univ. of Tokyo) / IKEBE Masayuki(Hokkaido Univ.) / HIROSE Yutaka(Panasonic) |
Secretary | Shunichiro Ohmi(AIST) / Makoto Ikeda(Nihon Univ.) / IKEBE Masayuki(Osaka Univ.) / HIROSE Yutaka(TSMC) |
Assistant | Taiji Noda(Panasonic) / Tomoyuki Suwa(Tohoku Univ.) / Kosuke Miyaji(Shinshu Univ.) / Yoshiaki Yoshihara(キオクシア) / Takeshi Kuboki(Kyushu Univ.) / KOMURO Takashi(Saitama Univ.) / SHIMONOMURA Kazuhiro(Ritsumeikan Univ.) / KAGAWA Keiichiro(Shizuoka Univ.) / TOKUDA Takashi(TITech) / KURODA Rihito(Tohoku Univ.) / HUNAZU Ryohei(NHK) / YAMASHITA Yuichiro(TSMC) |
Paper Information | |
Registration To | Technical Committee on Silicon Device and Materials / Technical Committee on Integrated Circuits and Devices / Technical Group on Information Sensing Technologies |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Approximation of Non-Linear Function for Hardware Implementation of Echo-State-Network |
Sub Title (in English) | |
Keyword(1) | Echo-State-Network |
Keyword(2) | Hyperbolic tangent |
Keyword(3) | Non-Linear Function Approximation |
1st Author's Name | Amartuvshin Bayasgalan |
1st Author's Affiliation | The University of Tokyo(UTokyo) |
2nd Author's Name | Makoto Ikeda |
2nd Author's Affiliation | The University of Tokyo(UTokyo) |
Date | 2021-08-17 |
Paper # | SDM2021-32,ICD2021-3 |
Volume (vol) | vol.121 |
Number (no) | SDM-138,ICD-139 |
Page | pp.pp.12-17(SDM), pp.12-17(ICD), |
#Pages | 6 |
Date of Issue | 2021-08-10 (SDM, ICD) |