| Presentation | 2020-12-01 Interpretability of deep neural networks with self-organizing map modules. Takahiro Sono, Keiichi Horio, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, the technology of neural networks has made great progress due to the improvement of computational power.As one of the features of these networks, more complex networks have been constructed, and many of the discrimination results are beyond human understanding.This makes it difficult to understand process in neural networks when we want to evaluate the clusters formed by human judgment, because there is no data to supervise the clusters, although we want to adapt them as classification problems.In this study, we constructed a full-layer visualization model using a neural network with self-organizing maps as a unit, and tested its interpretability. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | shape classification / neural network / self-organizing map / clustering / interpretability |
| Paper # | SIS2020-32 |
| Date of Issue | 2020-11-24 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2020/12/1(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Smart Personal Systems, etc. |
| Chair | Noriaki Suetake(Yamaguchi Univ.) |
| Vice Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.) |
| Secretary | Tomoaki Kimura(Kindai Univ.) / Naoto Sasaoka(National Inst. of Tech., Ube College) |
| Assistant | Yukihiro Bandoh(NTT) / Soh Yoshida(Kansai Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Interpretability of deep neural networks with self-organizing map modules. |
| Sub Title (in English) | |
| Keyword(1) | shape classification |
| Keyword(2) | neural network |
| Keyword(3) | self-organizing map |
| Keyword(4) | clustering |
| Keyword(5) | interpretability |
| 1st Author's Name | Takahiro Sono |
| 1st Author's Affiliation | Kyushu Institute of Technology(KIT) |
| 2nd Author's Name | Keiichi Horio |
| 2nd Author's Affiliation | Kyushu Institute of Technology(KIT) |
| Date | 2020-12-01 |
| Paper # | SIS2020-32 |
| Volume (vol) | vol.120 |
| Number (no) | SIS-269 |
| Page | pp.pp.27-30(SIS), |
| #Pages | 4 |
| Date of Issue | 2020-11-24 (SIS) |