| Presentation | 2022-01-21 Physical deep learning based on optimal control of dynamical systems Satoshi Sunada, Genki Furuhata, Tomoaki Niiyama, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | An underlying key factor of deep neural networks is the information propagation through the layers. This suggests a connection between deep neural networks and dynamical systems. In this presentation, we propose and demonstrate a pattern recognition approach based on optimal control of continuous-time dynamical systems. As a key example, we consider a delay system and show that it allows for information processing based on a virtual large-scale network in a physically single node with only a few control parameters. In addition, we discuss hardware implementation in an optoelectronic delay system. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Network / Deep Learning / Dynamical System / Optimal Control |
| Paper # | NLP2021-79,MICT2021-54,MBE2021-40 |
| 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) | Physical deep learning based on optimal control of dynamical systems |
| Sub Title (in English) | |
| Keyword(1) | Neural Network |
| Keyword(2) | Deep Learning |
| Keyword(3) | Dynamical System |
| Keyword(4) | Optimal Control |
| 1st Author's Name | Satoshi Sunada |
| 1st Author's Affiliation | Kanazawa University(Kanazawa Univ.) |
| 2nd Author's Name | Genki Furuhata |
| 2nd Author's Affiliation | Kanazawa University(Kanazawa Univ.) |
| 3rd Author's Name | Tomoaki Niiyama |
| 3rd Author's Affiliation | Kanazawa University(Kanazawa Univ.) |
| Date | 2022-01-21 |
| Paper # | NLP2021-79,MICT2021-54,MBE2021-40 |
| Volume (vol) | vol.121 |
| Number (no) | NLP-335,MICT-336,MBE-337 |
| Page | pp.pp.36-36(NLP), pp.36-36(MICT), pp.36-36(MBE), |
| #Pages | 1 |
| Date of Issue | 2022-01-14 (NLP, MICT, MBE) |