| Presentation | 2021-11-18 Effects of spike transmission delay in spiking reservoir networks Satsuki Tamura, Tsubo Yasuhiro, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Spiking neural network is expected as a candidate of information processing systems with low-energy consumption. However, even the state-of-the-art system of spiking neural networks is inferior to conventional artificial neural networks with time-discrete nature. To improve the learning ability of spiking neural networks, we introduce spike transmission delays inspired by the recent neuroscientific result that the myelin sheath morphology involved in spike transmission delay changed with memory consolidation task. We investigated the effect of the distribution of signal transmission delay on the learning ability of the spiking reservoir network. We found that a signal transmission delay with a temporal distribution on the readout connections from reservoir units to an output unit improved the learning performance for 1-dimensional temporal sequences. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | liquid state machine / myelin sheath / spiking neural network / time series learning |
| Paper # | CCS2021-22 |
| Date of Issue | 2021-11-11 (CCS) |
| Conference Information | |
| Committee | CCS |
|---|---|
| Conference Date | 2021/11/18(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Osaka Univ. |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tetsuya Asai(Hokkaido Univ.) |
| Vice Chair | Megumi Akai(Hokkaido Univ.) / Masaki Aida(TMU) |
| Secretary | Megumi Akai(TDK) / Masaki Aida(Mie Univ.) |
| Assistant | Hidehiro Nakano(Tokyo City Univ.) / Hiroyasu Ando(Tsukuba Univ.) / Takashi Matsubara(Osaka Univ.) / Sumiko Miyata(Shibaura Inst. of Tech.) |
| 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) | Effects of spike transmission delay in spiking reservoir networks |
| Sub Title (in English) | |
| Keyword(1) | liquid state machine |
| Keyword(2) | myelin sheath |
| Keyword(3) | spiking neural network |
| Keyword(4) | time series learning |
| 1st Author's Name | Satsuki Tamura |
| 1st Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| 2nd Author's Name | Tsubo Yasuhiro |
| 2nd Author's Affiliation | Ritsumeikan University(Ritsumeikan Univ.) |
| Date | 2021-11-18 |
| Paper # | CCS2021-22 |
| Volume (vol) | vol.121 |
| Number (no) | CCS-253 |
| Page | pp.pp.26-30(CCS), |
| #Pages | 5 |
| Date of Issue | 2021-11-11 (CCS) |