| Presentation | 2015-12-19 A Learning Method for Extended SpikeProp without Redundant Spikes Takashi Matsumoto, Haruhiko Takase, Hiroharu Kawanaka, Shinji Tsuruoka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | SpikeProp, which is proposed by Booij, is a kind of spiking neural networks. It can learn the timing of output spikes, but cannot adjust the number of output spikes. Our research group has discussed the problem and proposed a learning method that can adjust both timing and number of spikes. However, its learning performance depends on the initial network structure (the number of hidden units, time delay, the number of sub-connections, and so on). In this article, we discuss the problem, especially the number of sub-connections. And, we proposed the method that suppress unnecessary sub-connections during its training according to spike timing. By some simple experiments, we show the effectiveness of our method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Spiking Neural Network / SpikeProp / Time Series Imformation Processing / Learning Algorithm |
| Paper # | NC2015-53 |
| Date of Issue | 2015-12-12 (NC) |
| Conference Information | |
| Committee | MBE / NC |
|---|---|
| Conference Date | 2015/12/19(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Nagoya Institute of Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tetsuo Kobayashi(Kyoto Univ.) / Toshimichi Saito(Hosei Univ.) |
| Vice Chair | Yutaka Fukuoka(Kogakuin Univ.) / Shigeo Sato(Tohoku Univ.) |
| Secretary | Yutaka Fukuoka(akita noken) / Shigeo Sato(Kogakuin Univ.) |
| Assistant | Takenori Oida(Kyoto Univ.) / Ryota Horie(Shibaura Inst. of Tech.) / Hiroyuki Kanbara(Tokyo Inst. of Tech.) / Hisanao Akima(Tohoku 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) | A Learning Method for Extended SpikeProp without Redundant Spikes |
| Sub Title (in English) | A Discussion on Methods to Suppress Redundant Connections |
| Keyword(1) | Spiking Neural Network |
| Keyword(2) | SpikeProp |
| Keyword(3) | Time Series Imformation Processing |
| Keyword(4) | Learning Algorithm |
| 1st Author's Name | Takashi Matsumoto |
| 1st Author's Affiliation | Mie University(Mie Univ.) |
| 2nd Author's Name | Haruhiko Takase |
| 2nd Author's Affiliation | Mie University(Mie Univ.) |
| 3rd Author's Name | Hiroharu Kawanaka |
| 3rd Author's Affiliation | Mie University(Mie Univ.) |
| 4th Author's Name | Shinji Tsuruoka |
| 4th Author's Affiliation | Mie University(Mie Univ.) |
| Date | 2015-12-19 |
| Paper # | NC2015-53 |
| Volume (vol) | vol.115 |
| Number (no) | NC-384 |
| Page | pp.pp.43-48(NC), |
| #Pages | 6 |
| Date of Issue | 2015-12-12 (NC) |