| Presentation | 2023-03-02 Non-uniqueness of solutions in Physics-informed neural networks Shuichiro Tsuda, Toshiyuki Tanaka, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | PINN is a method of acquiring a neural network that represents the solution of a differential equation by including a constraint term derived from the differential equation in the learning loss function and is applied to the analysis of various physical phenomena described by differential equations. In this study, we discuss the properties of solutions obtained by PINN when solving initial value and boundary value problems of differential equations. We show that the solutions obtained by PINN are not uniquely determined. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Physics-informed neural networks |
| Paper # | PRMU2022-81,IBISML2022-88 |
| Date of Issue | 2023-02-23 (PRMU, IBISML) |
| Conference Information | |
| Committee | PRMU / IBISML / IPSJ-CVIM |
|---|---|
| Conference Date | 2023/3/2(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Future University Hakodate |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Seiichi Uchida(Kyushu Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
| Vice Chair | Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo) / Toshihiro Kamishima(NTT) / Koji Tsuda(Hokkaido Univ.) |
| Assistant | Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Non-uniqueness of solutions in Physics-informed neural networks |
| Sub Title (in English) | |
| Keyword(1) | Physics-informed neural networks |
| 1st Author's Name | Shuichiro Tsuda |
| 1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
| 2nd Author's Name | Toshiyuki Tanaka |
| 2nd Author's Affiliation | Kyoto University(Kyoto Univ.) |
| Date | 2023-03-02 |
| Paper # | PRMU2022-81,IBISML2022-88 |
| Volume (vol) | vol.122 |
| Number (no) | PRMU-404,IBISML-405 |
| Page | pp.pp.125-128(PRMU), pp.125-128(IBISML), |
| #Pages | 4 |
| Date of Issue | 2023-02-23 (PRMU, IBISML) |