Presentation | 2020-03-06 Performance Evaluation of Echo State Networks with Hardware Reservoirs Yuki Kume, Song Bian, Kenta Nagura, Takashi Sato, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Echo state Network (ESN), a class of recurrent neural network, is characteristic in its use of a reservoir having random and constant weights during training and inference computations. ESN is suitable for hardware implementation because of its low training cost and simple neural architecture. Recently, MOS-ESN is proposed to implement ESN by using hardware reservoir consists of physical metal-oxide-semiconductor field effect transistors (MOSFETs). The variations in MOSFETs are used as the source of the random weights without the need to manually tune the parameters for stability. MOS-ESN and the related Dual-MOS-ESN architecture demonstrates high inference accuracy on a particular dataset, but the evaluation is inadequate. In this paper, we conduct a more thorough performance evaluation for Dual-MOS-ESN and other similar hardware reservoir structures. Through the evaluation, we show the effectiveness of the dual architecture across datasets in comparison with other MOS-ESN architectures. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | echo state network / reservoir computing / recurrent neural network / MOSFET / crossbar array |
Paper # | VLD2019-136,HWS2019-109 |
Date of Issue | 2020-02-26 (VLD, HWS) |
Conference Information | |
Committee | HWS / VLD |
---|---|
Conference Date | 2020/3/4(4days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Ken Seinen Kaikan |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Design Technology for System-on-Silicon, Hardware Security, etc. |
Chair | Shinichi Kawamura(Toshiba) / Nozomu Togawa(Waseda Univ.) |
Vice Chair | Makoto Ikeda(Univ. of Tokyo) / Yasuhisa Shimazaki(Renesas Electronics) / Daisuke Fukuda(Fujitsu Labs.) |
Secretary | Makoto Ikeda(SECOM) / Yasuhisa Shimazaki(Kyushu Univ.) / Daisuke Fukuda(Univ. of Aizu) |
Assistant | / Kazuki Ikeda(Hitachi) |
Paper Information | |
Registration To | Technical Committee on Hardware Security / Technical Committee on VLSI Design Technologies |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Performance Evaluation of Echo State Networks with Hardware Reservoirs |
Sub Title (in English) | |
Keyword(1) | echo state network |
Keyword(2) | reservoir computing |
Keyword(3) | recurrent neural network |
Keyword(4) | MOSFET |
Keyword(5) | crossbar array |
1st Author's Name | Yuki Kume |
1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
2nd Author's Name | Song Bian |
2nd Author's Affiliation | Kyoto University(Kyoto Univ.) |
3rd Author's Name | Kenta Nagura |
3rd Author's Affiliation | Kyoto University(Kyoto Univ.) |
4th Author's Name | Takashi Sato |
4th Author's Affiliation | Kyoto University(Kyoto Univ.) |
Date | 2020-03-06 |
Paper # | VLD2019-136,HWS2019-109 |
Volume (vol) | vol.119 |
Number (no) | VLD-443,HWS-444 |
Page | pp.pp.245-250(VLD), pp.245-250(HWS), |
#Pages | 6 |
Date of Issue | 2020-02-26 (VLD, HWS) |