| Presentation | 2022-01-22 On the relationship between properties of the hysteresis reservoir layer and the training output sequence Tsukasa Saito, Kenya Jin'no, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Reservoir computing is a type of machine learning model that can be trained at low cost and fast. However, conventional reservoir computing often do not achieve the memory capacity and nonlinearity required. To solve this prob- lem, we proposed hysteresis reservoir computing, a model in which conventional reservoir neurons are replaced by hysteresis neurons, which generate various output sequences by changing parameters. In this paper, we confirm the dynamics generated by changing the parameters of the hysteresis element in the hysteresis reservoir layer. The experimental results indicate that changing the parameters improves the learning ability and can represent specific series of data. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | reservoir computing / time series / oscillator / time constant / complex |
| Paper # | NLP2021-99,MICT2021-74,MBE2021-60 |
| Date of Issue | 2022-01-14 (NLP, MICT, MBE) |
| Conference Information | |
| Committee | NLP / MICT / MBE / NC |
|---|---|
| Conference Date | 2022/1/21(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Takuji Kosaka(Chukyo Univ.) / Eisuke Hanada(Saga Univ.) / Ryuhei Okuno(Setsunan Univ.) / Rieko Osu(Waseda Univ.) |
| Vice Chair | Akio Tsuneda(Kumamoto Univ.) / Hirokazu Tanaka(Hiroshima City Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) / Junichi Hori(Niigata Univ.) / Hiroshi Yamakawa(Univ of Tokyo) |
| Secretary | Akio Tsuneda(Kagawa Univ.) / Hirokazu Tanaka(Sojo Univ.) / Daisuke Anzai(Yokohama National Univ.) / Junichi Hori(KISTEC) / Hiroshi Yamakawa(Osaka Electro-Communication Univ) |
| Assistant | Hideyuki Kato(Oita Univ.) / Yuichi Yokoi(Nagasaki Univ.) / Takahiro Ito(Hiroshima City Univ) / Kento Takabayashi(Okayama Pref. Univ.) / Takuya Nishikawa(National Cerebral and Cardiovascular Center Hospital) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Emi Yuda(Tohoku Univ) / Nobuhiko Wagatsuma(Toho Univ.) / Tomoki Kurikawa(KMU) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems / Technical Committee on Healthcare and Medical Information Communication Technology / Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | On the relationship between properties of the hysteresis reservoir layer and the training output sequence |
| Sub Title (in English) | |
| Keyword(1) | reservoir computing |
| Keyword(2) | time series |
| Keyword(3) | oscillator |
| Keyword(4) | time constant |
| Keyword(5) | complex |
| 1st Author's Name | Tsukasa Saito |
| 1st Author's Affiliation | Tokyo City University(Tokyo City Univ) |
| 2nd Author's Name | Kenya Jin'no |
| 2nd Author's Affiliation | Tokyo City University(Tokyo City Univ) |
| Date | 2022-01-22 |
| Paper # | NLP2021-99,MICT2021-74,MBE2021-60 |
| Volume (vol) | vol.121 |
| Number (no) | NLP-335,MICT-336,MBE-337 |
| Page | pp.pp.121-124(NLP), pp.121-124(MICT), pp.121-124(MBE), |
| #Pages | 4 |
| Date of Issue | 2022-01-14 (NLP, MICT, MBE) |