| Presentation | 2017-10-07 Robust memory capacity in echo state networks with a small-world topology Yuji Kawai, Jihoon Park, Minoru Asada, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A small-world (SW) topology was found in the cortical neural connectivity. However, the role of the topology in neural information processing has been left unclear. We investigate the memory capacity of an echo state network (ESN) within the SW topology. In order to elucidate the potential of the SW topology, we limit the number of the input and output nodes in the ESN, segregate output nodes from input ones, and add noise to input nodes. The SW-ESN maintained the memory capacity even when the input and output nodes were segregated. This memory capacity was larger and more robust against the input noise than that of the ESN with random connectivity. These results suggest that the SW topology is essential for holding large memory capacity between input and output regions under sensor noise. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | echo state network / small-world network / reservoir computing / recurrent neural network / memory capacity |
| Paper # | NC2017-20 |
| Date of Issue | 2017-09-30 (NC) |
| Conference Information | |
| Committee | MBE / NC |
|---|---|
| Conference Date | 2017/10/7(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Osaka Electro-Communication University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | ME, general |
| Chair | Kazuki Nakajima(Univ. of Toyama) / Masafumi Hagiwara(Keio Univ.) |
| Vice Chair | Masaki Kyoso(TCU) / Yutaka Hirata(Chubu Univ.) |
| Secretary | Masaki Kyoso(Toyama Pref. Univ.) / Yutaka Hirata(Kindai Univ.) |
| Assistant | Kim Juhyon(Univ. of Toyama) / Takumi Kobayashi(YNU) / Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu Univ.) |
| Paper Information | |
| Registration To | 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) | Robust memory capacity in echo state networks with a small-world topology |
| Sub Title (in English) | |
| Keyword(1) | echo state network |
| Keyword(2) | small-world network |
| Keyword(3) | reservoir computing |
| Keyword(4) | recurrent neural network |
| Keyword(5) | memory capacity |
| 1st Author's Name | Yuji Kawai |
| 1st Author's Affiliation | Osaka University(Osaka Univ.) |
| 2nd Author's Name | Jihoon Park |
| 2nd Author's Affiliation | Osaka University(Osaka Univ.) |
| 3rd Author's Name | Minoru Asada |
| 3rd Author's Affiliation | Osaka University(Osaka Univ.) |
| Date | 2017-10-07 |
| Paper # | NC2017-20 |
| Volume (vol) | vol.117 |
| Number (no) | NC-231 |
| Page | pp.pp.1-6(NC), |
| #Pages | 6 |
| Date of Issue | 2017-09-30 (NC) |