| Presentation | 2020-12-02 Investigation of oxide semiconductor thin film synapse using STDP learning method Tetsuya Katagiri, Daiki Yamakawa, Kenta Yatida, Kazuki Morigaki, Mutsumi Kimura, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Neuromorphic hardware is expected as low power consumption and high performance hardware that does not have the power consumption and robustness problems of artificial intelligence running on current von Neumann computers. In previous research, we succeeded in character recognition learning using a device that uses amorphous In-Ga-Zn-O(a-IGZO), which is an oxide semiconductor, as a synaptic element. In this study, we investigated whether a-IGZO can be used as a synaptic element in a spiking neural network(SNN) that using spike timing-dependent plasticity (STDP) with the aim of further reducing power consumption and improving performance. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Network / Neuromorphic / Synapse / Spike Timing Dependent Plasticity / IGZO |
| Paper # | EID2020-6,SDM2020-40 |
| Date of Issue | 2020-11-25 (EID, SDM) |
| Conference Information | |
| Committee | EID / SDM / ITE-IDY |
|---|---|
| Conference Date | 2020/12/2(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Rumiko Yamaguchi(Akita Univ.) / Hiroshige Hirano(TowerPartners Semiconductor) |
| Vice Chair | Masahiro Yamaguchi(Tokyo Inst. of Tech.) / Tomoyuki Ishihara(Japan Display) / Shunichiro Ohmi(Tokyo Inst. of Tech.) |
| Secretary | Masahiro Yamaguchi(NTT) / Tomoyuki Ishihara(NHK) / Shunichiro Ohmi(AIST) / (Nihon Univ.) |
| Assistant | Mutsumi Kimura(Ryukoku Univ.) / Tomokazu Shiga(Univ. of Electro-Comm.) / Hiroko Kominami(Shizuoka Univ.) / Masanobu Mizusaki(SHARP) / Masayuki Kanbara(NAIST) / Taiji Noda(Panasonic) / Tomoyuki Suwa(Tohoku Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Electronic Information Displays / Technical Committee on Silicon Device and Materials / Technical Group on Information Display |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Investigation of oxide semiconductor thin film synapse using STDP learning method |
| Sub Title (in English) | |
| Keyword(1) | Neural Network |
| Keyword(2) | Neuromorphic |
| Keyword(3) | Synapse |
| Keyword(4) | Spike Timing Dependent Plasticity |
| Keyword(5) | IGZO |
| 1st Author's Name | Tetsuya Katagiri |
| 1st Author's Affiliation | Ryukoku University(Ryukoku Univ.) |
| 2nd Author's Name | Daiki Yamakawa |
| 2nd Author's Affiliation | Ryukoku University(Ryukoku Univ.) |
| 3rd Author's Name | Kenta Yatida |
| 3rd Author's Affiliation | Ryukoku University(Ryukoku Univ.) |
| 4th Author's Name | Kazuki Morigaki |
| 4th Author's Affiliation | Ryukoku University(Ryukoku Univ.) |
| 5th Author's Name | Mutsumi Kimura |
| 5th Author's Affiliation | Ryukoku University(Ryukoku Univ.) |
| Date | 2020-12-02 |
| Paper # | EID2020-6,SDM2020-40 |
| Volume (vol) | vol.120 |
| Number (no) | EID-272,SDM-273 |
| Page | pp.pp.21-24(EID), pp.21-24(SDM), |
| #Pages | 4 |
| Date of Issue | 2020-11-25 (EID, SDM) |