| Presentation | 2020-10-29 Numerical research on effects of quantization in SNN learned by backpropagation Yumi Watanabe, Jun Ohkubo, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | There are many studies to quantize the parameters of neural networks. For example, while there are methods of quantizing at the time of learning, there are also methods of quantizing learned parameters, which have advantages such as memory reduction and execution time reduction. In recent years, research on spiking neural networks (SNN) has been promoted by proposing approximation methods for the backpropagation. However, there is not much research on quantization. In this study, we numerically evaluate how the quantization of weights affects the performance after training the SNN learned by backpropagation. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Quantization / Backpropagation / Neural Network / Spiking Neural Network(SNN) |
| Paper # | NC2020-14 |
| Date of Issue | 2020-10-22 (NC) |
| Conference Information | |
| Committee | MBE / NC / NLP / CAS |
|---|---|
| Conference Date | 2020/10/29(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | ME，NC，CAS，NLP |
| Chair | Takashi Watanabe(Tohoku Univ.) / Kazuyuki Samejima(Tamagawa Univ) / Kiyohisa Natsume(Kyushu Inst. of Tech.) / Yasuhiro Takashima(Univ. of Kitakyushu) |
| Vice Chair | Ryuhei Okuno(Setsunan Univ.) / Rieko Osu(Waseda Univ.) / Takuji Kosaka(Chukyo Univ.) / Hiroki Sato(Sony LSI Design) |
| Secretary | Ryuhei Okuno(Akita-noken) / Rieko Osu(NTT) / Takuji Kosaka(ATR) / Hiroki Sato(Kyushu Inst. of Tech.) |
| Assistant | Akihiro Karashima(Tohoku Inst. of Tech.) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Ken Takiyama(TUAT) / Nobuhiko Wagatsuma(Toho Univ.) / Toshikaza Samura(Yamaguchi Univ.) / Hideyuki Kato(Oita Univ.) / Motoi Yamaguchi(TECHNOPRO) / Yohei Nakamura(Hitachi) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing / Technical Committee on Nonlinear Problems / Technical Committee on Circuits and Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Numerical research on effects of quantization in SNN learned by backpropagation |
| Sub Title (in English) | |
| Keyword(1) | Quantization |
| Keyword(2) | Backpropagation |
| Keyword(3) | Neural Network |
| Keyword(4) | Spiking Neural Network(SNN) |
| 1st Author's Name | Yumi Watanabe |
| 1st Author's Affiliation | Saitama University(Saitama Univ.) |
| 2nd Author's Name | Jun Ohkubo |
| 2nd Author's Affiliation | Saitama University(Saitama Univ.) |
| Date | 2020-10-29 |
| Paper # | NC2020-14 |
| Volume (vol) | vol.120 |
| Number (no) | NC-216 |
| Page | pp.pp.29-33(NC), |
| #Pages | 5 |
| Date of Issue | 2020-10-22 (NC) |