| Presentation | 2020-06-18 On numerical approximated solutions of an ordinary differential\ equation using a LSTM neural network Kazuya Ozawa, Kaito Isogai, Hideaki Okazaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recurrent neural networks (RNNs) were demonstrated to provide good accuracy when modeling nonlinear circuits. However, since the trainingalgorithm of RNN needs the backpropogation through time(BPTT), this has a Vanishing gradient problem. Long-Short Term Memory (LSTM) which is a type of RNNs uses several gated units to avoid this probem. In this paper, LSTM is applied to estimate perodic behavior of Colpitts oscillator. The numerical approximated solutions of Colpitts oscillator ordinary differential equation using the LSTM neural network are discussed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | LSTM Neural Network / Colpitts Oscillator / Differential equations / Approximation |
| Paper # | CAS2020-2,VLD2020-2,SIP2020-18,MSS2020-2 |
| Date of Issue | 2020-06-11 (CAS, VLD, SIP, MSS) |
| Conference Information | |
| Committee | MSS / CAS / SIP / VLD |
|---|---|
| Conference Date | 2020/6/18(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online Meetig |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shigemasa Takai(Osaka Univ.) / Yasuhiro Takashima(Univ. of Kitakyushu) / Naoyuki Aikawa(TUS) / Daisuke Fukuda(Fujitsu Labs.) |
| Vice Chair | Atsuo Ozaki(Osaka Inst. of Tech.) / Hiroki Sato(Sony LSI Design) / Kazunori Hayashi(Osaka City Univ) / Yukihiro Bandou(NTT) / Kazutoshi Kobayashi(Kyoto Inst. of Tech.) |
| Secretary | Atsuo Ozaki(Setsunan Univ.) / Hiroki Sato(Hokkaido Univ.) / Kazunori Hayashi(Yamanashi Univ.) / Yukihiro Bandou(Sony LSI Design) / Kazutoshi Kobayashi(Hiroshima Univ.) |
| Assistant | Naoki Hayashi(Osaka Univ.) / Motoi Yamaguchi(TECHNOPRO) / Yohei Nakamura(Hitachi) / Kenjiro Sugimoto(Waseda Univ.) / Kazuki Ikeda(Hitachi) |
| Paper Information | |
| Registration To | Technical Committee on Mathematical Systems Science and its applications / Technical Committee on Circuits and Systems / Technical Committee on Signal Processing / Technical Committee on VLSI Design Technologies |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | On numerical approximated solutions of an ordinary differential\ equation using a LSTM neural network |
| Sub Title (in English) | |
| Keyword(1) | LSTM Neural Network |
| Keyword(2) | Colpitts Oscillator |
| Keyword(3) | Differential equations |
| Keyword(4) | Approximation |
| 1st Author's Name | Kazuya Ozawa |
| 1st Author's Affiliation | Shonan Institute of Technology(SIT) |
| 2nd Author's Name | Kaito Isogai |
| 2nd Author's Affiliation | Shonan Institute of Technology(SIT) |
| 3rd Author's Name | Hideaki Okazaki |
| 3rd Author's Affiliation | Shonan Institute of Technology(SIT) |
| Date | 2020-06-18 |
| Paper # | CAS2020-2,VLD2020-2,SIP2020-18,MSS2020-2 |
| Volume (vol) | vol.120 |
| Number (no) | CAS-65,VLD-66,SIP-67,MSS-68 |
| Page | pp.pp.7-9(CAS), pp.7-9(VLD), pp.7-9(SIP), pp.7-9(MSS), |
| #Pages | 3 |
| Date of Issue | 2020-06-11 (CAS, VLD, SIP, MSS) |