| Presentation | 2020-11-26 On an approximating polynomials by a Pseudo Residual Neural Network with a Power Activation Function Kazuya Ozawa, Kaito Isogai, Hideaki Okazaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Since a series of successes of Deep neural networks (DNNs) with rectified linear units (ReLUs), many approximations by NNs with ReLUs, or rectified power units (RePUs) have been focused on. Further deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors, when using identity mappings as the skip connections and after-addition activation. In this paper, approximating polynomials by a pseudo residual network (PResN) such as a NN with power units (PUs) ? a NN with ReLUs + another NN with ReLUs when using identity mappings as the skip connections of the former NN with PUs and after-addition activation, is discussed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Network / Residual network / pseudo residual network, / Polynomial function enclosure |
| Paper # | CAS2020-31,MSS2020-23 |
| Date of Issue | 2020-11-18 (CAS, MSS) |
| Conference Information | |
| Committee | MSS / CAS / IPSJ-AL |
|---|---|
| Conference Date | 2020/11/25(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shigemasa Takai(Osaka Univ.) / Yasuhiro Takashima(Univ. of Kitakyushu) |
| Vice Chair | Atsuo Ozaki(Osaka Inst. of Tech.) / Hiroki Sato(Sony LSI Design) |
| Secretary | Atsuo Ozaki(Setsunan Univ.) / Hiroki Sato(Hokkaido Univ.) / (Yamanashi Univ.) |
| Assistant | Naoki Hayashi(Osaka Univ.) / Motoi Yamaguchi(TECHNOPRO) / Yohei Nakamura(Hitachi) |
| Paper Information | |
| Registration To | Technical Committee on Mathematical Systems Science and its applications / Technical Committee on Circuits and Systems / Special Interest Group on Algorithms |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | On an approximating polynomials by a Pseudo Residual Neural Network with a Power Activation Function |
| Sub Title (in English) | |
| Keyword(1) | Neural Network |
| Keyword(2) | Residual network |
| Keyword(3) | pseudo residual network, |
| Keyword(4) | Polynomial function enclosure |
| 1st Author's Name | Kazuya Ozawa |
| 1st Author's Affiliation | Shonan Institute of Technology(Shonan Inst. Tech) |
| 2nd Author's Name | Kaito Isogai |
| 2nd Author's Affiliation | Shonan Institute of Technology(Shonan Inst. Tech) |
| 3rd Author's Name | Hideaki Okazaki |
| 3rd Author's Affiliation | Shonan Institute of Technology(Shonan Inst. Tech) |
| Date | 2020-11-26 |
| Paper # | CAS2020-31,MSS2020-23 |
| Volume (vol) | vol.120 |
| Number (no) | CAS-245,MSS-246 |
| Page | pp.pp.68-72(CAS), pp.68-72(MSS), |
| #Pages | 5 |
| Date of Issue | 2020-11-18 (CAS, MSS) |