| Presentation | 2022-01-23 Deep learning of mixture of continuous and categorical data with regularizers added to the cost function and evaluation of the effectiveness of sparse modeling Masumi Ishikawa, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Deep learning has a serious drawback in that the resulting models tend to be a black box, hence hard to understand. A sparse modeling approach is expected to ameliorate the drawback. Various regularization terms are proposed so far. The paper proposes to use the concept of Pareto optimality composed of data fitting and the sparseness of models for judging the effectiveness of regularization terms using US census data. Compared to the most popular L1-norm to connection weights, the selective L1-norm to connection weights is better, off-diagonal covariance or KL divergence of hidden outputs are yet better, and the selective L1 norm or selective L2 norm to hidden outputs are the best. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning / Black-box model / Explainable / Sparse modeling / Regularizers |
| Paper # | NC2021-45 |
| Date of Issue | 2022-01-14 (NC) |
| Conference Information | |
| Committee | NLP / MICT / MBE / NC |
|---|---|
| Conference Date | 2022/1/21(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Takuji Kosaka(Chukyo Univ.) / Eisuke Hanada(Saga Univ.) / Ryuhei Okuno(Setsunan Univ.) / Rieko Osu(Waseda Univ.) |
| Vice Chair | Akio Tsuneda(Kumamoto Univ.) / Hirokazu Tanaka(Hiroshima City Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) / Junichi Hori(Niigata Univ.) / Hiroshi Yamakawa(Univ of Tokyo) |
| Secretary | Akio Tsuneda(Kagawa Univ.) / Hirokazu Tanaka(Sojo Univ.) / Daisuke Anzai(Yokohama National Univ.) / Junichi Hori(KISTEC) / Hiroshi Yamakawa(Osaka Electro-Communication Univ) |
| Assistant | Hideyuki Kato(Oita Univ.) / Yuichi Yokoi(Nagasaki Univ.) / Takahiro Ito(Hiroshima City Univ) / Kento Takabayashi(Okayama Pref. Univ.) / Takuya Nishikawa(National Cerebral and Cardiovascular Center Hospital) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Emi Yuda(Tohoku Univ) / Nobuhiko Wagatsuma(Toho Univ.) / Tomoki Kurikawa(KMU) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems / Technical Committee on Healthcare and Medical Information Communication Technology / Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Deep learning of mixture of continuous and categorical data with regularizers added to the cost function and evaluation of the effectiveness of sparse modeling |
| Sub Title (in English) | |
| Keyword(1) | Deep learning |
| Keyword(2) | Black-box model |
| Keyword(3) | Explainable |
| Keyword(4) | Sparse modeling |
| Keyword(5) | Regularizers |
| 1st Author's Name | Masumi Ishikawa |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| Date | 2022-01-23 |
| Paper # | NC2021-45 |
| Volume (vol) | vol.121 |
| Number (no) | NC-338 |
| Page | pp.pp.65-70(NC), |
| #Pages | 6 |
| Date of Issue | 2022-01-14 (NC) |