| Presentation | 2020-03-26 Reservoir computing using fluid motion Keita Kohashi, Masanobu Inubushi, Susumu Goto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Reservoir computing (RC) is a machine learning method using nonlinear dynamical systems, which is effective for time-series processing. As a novel method of Natural Computing, various physical phenomena as the nonlinear dynamics have been utilized in the framework of RC so far. However, little is known about information processing performance by RC with spatiotemporal dynamics. In this study, we show that RC using fluid motion as spatiotemporal dynamics is effective for a variety of machine learning tasks including time-series prediction and speech recognition. Moreover, we study a relationship between physical properties of fluid motion and information processing performance, and discuss key issues inherent in the implementation of RC with spatiotemporal dynamics. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Reservoir computing / Echo state network / Machine learning / Fluid motion / Lyapunov analysis |
| Paper # | CCS2019-40 |
| Date of Issue | 2020-03-18 (CCS) |
| Conference Information | |
| Committee | CCS |
|---|---|
| Conference Date | 2020/3/25(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Hosei Univ. Ichigaya Campus |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Natural Computing, etc. |
| Chair | Makoto Naruse(NICT) |
| Vice Chair | Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Tetsuya Asai(Hokkaido Univ.) |
| Secretary | Shigeki Shiokawa(Hiroshima City Univ.) / Tetsuya Asai(Kanagawa Inst. of Tech.) |
| Assistant | Hidehiro Nakano(Tokyo City Univ.) / Kazuki Nakada(Tsukuba Univ. of Tech.) / Hiroyasu Ando(Tsukuba Univ.) / Takashi Matsubara(Kobe Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Complex Communication Sciences |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Reservoir computing using fluid motion |
| Sub Title (in English) | |
| Keyword(1) | Reservoir computing |
| Keyword(2) | Echo state network |
| Keyword(3) | Machine learning |
| Keyword(4) | Fluid motion |
| Keyword(5) | Lyapunov analysis |
| 1st Author's Name | Keita Kohashi |
| 1st Author's Affiliation | Osaka University(Osaka Univ.) |
| 2nd Author's Name | Masanobu Inubushi |
| 2nd Author's Affiliation | Osaka University(Osaka Univ.) |
| 3rd Author's Name | Susumu Goto |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2020-03-26 |
| Paper # | CCS2019-40 |
| Volume (vol) | vol.119 |
| Number (no) | CCS-485 |
| Page | pp.pp.25-27(CCS), |
| #Pages | 3 |
| Date of Issue | 2020-03-18 (CCS) |