| Presentation | 2018-09-21 [Invited Talk] Reservoir Computing: Theory, Physical Implementations, and Applications Kohei Nakajima, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Reservoir Computing (RC) has been proposed as a framework for training recurrent neural networks. In this framework, low-dimensional input is projected to a high-dimensional dynamical system, which is referred to as a reservoir. If the dynamics of the reservoir involve enough nonlinearity and if enough memory is available, emulating nonlinear dynamical systems requires only the addition of a linear, static readout from the high-dimensional state space of the reservoir. Due to its generic nature, RC is not limited to digital simulations of neural networks. In fact, any high-dimensional dynamical system, including a system utilizing physical dynamics, can serve as a reservoir if it has the appropriate properties. In this talk, we will introduce the recent advancement of RC by presenting a number of new applications in the field of soft robotics. This short paper aims to introduce the basics of the framework by explaining a benchmark platform called the echo state network. The use of this example should help to clarify the advanced content in the talk from its very foundation. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Reservoir computing / Physical reservoir computing / Recurrent neural network / Soft robotics / Soft robots / Nonlinear dynamics / Morphological computation |
| Paper # | PRMU2018-60,IBISML2018-37 |
| Date of Issue | 2018-09-13 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2018/9/20(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Hisashi Kashima(Kyoto Univ.) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] Reservoir Computing: Theory, Physical Implementations, and Applications |
| Sub Title (in English) | |
| Keyword(1) | Reservoir computing |
| Keyword(2) | Physical reservoir computing |
| Keyword(3) | Recurrent neural network |
| Keyword(4) | Soft robotics |
| Keyword(5) | Soft robots |
| Keyword(6) | Nonlinear dynamics |
| Keyword(7) | Morphological computation |
| 1st Author's Name | Kohei Nakajima |
| 1st Author's Affiliation | The University of Tokyo(Univ. Tokyo) |
| Date | 2018-09-21 |
| Paper # | PRMU2018-60,IBISML2018-37 |
| Volume (vol) | vol.118 |
| Number (no) | PRMU-219,IBISML-220 |
| Page | pp.pp.149-154(PRMU), pp.149-154(IBISML), |
| #Pages | 6 |
| Date of Issue | 2018-09-13 (PRMU, IBISML) |