| Presentation | 2016-06-13 A Method for Adding Classification Classes in Random Forests Ryota Ozaki, Yukihiro Tsuboshita, Noriji Kato, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In estimating classes using Random Forests, it is necessary to re-create decision trees with the data of all classes when target data increases and classification classes are added. We propose a method for adding classification classes in Random Forests that does not re-create the decision trees. Leaf nodes of the proposed method have class frequency information and learning data statistics information. According to the proposed method, it is possible to learn RF with only the data of added classes by updating these information. In addition, we dynamically suppress decrease of class estimate accuracy by correcting class frequency information with the relationship between input data and the learning data statistics information. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Machine Learning / Random Forests / Deep Learning / Incremental Learning |
| Paper # | PRMU2016-42,SP2016-8,WIT2016-8 |
| Date of Issue | 2016-06-06 (PRMU, SP, WIT) |
| Conference Information | |
| Committee | PRMU / SP / WIT / ASJ-H |
|---|---|
| Conference Date | 2016/6/13(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Eisaku Maeda(NTT) / Kazunori Mano(Shibaura Inst. of Tech.) / Kiyohiko Nunokawa(Tokyo International Univ.) |
| Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / Hiroki Mori(Utsunomiya Univ.) / Chikamune Wada(Kyushu Inst. of Tech.) |
| Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / Hiroki Mori(Kobe Univ.) / Chikamune Wada(Shizuoka Univ.) / (Nagoya Inst. of Tech.) |
| Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / Taichi Asami(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Speech / Technical Committee on Well-being Information Technology / Auditory Research Meeting |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Method for Adding Classification Classes in Random Forests |
| Sub Title (in English) | |
| Keyword(1) | Machine Learning |
| Keyword(2) | Random Forests |
| Keyword(3) | Deep Learning |
| Keyword(4) | Incremental Learning |
| 1st Author's Name | Ryota Ozaki |
| 1st Author's Affiliation | Fuji Xerox Co., Ltd.(Fuji Xerox) |
| 2nd Author's Name | Yukihiro Tsuboshita |
| 2nd Author's Affiliation | Fuji Xerox Co., Ltd.(Fuji Xerox) |
| 3rd Author's Name | Noriji Kato |
| 3rd Author's Affiliation | Fuji Xerox Co., Ltd.(Fuji Xerox) |
| Date | 2016-06-13 |
| Paper # | PRMU2016-42,SP2016-8,WIT2016-8 |
| Volume (vol) | vol.116 |
| Number (no) | PRMU-89,SP-90,WIT-91 |
| Page | pp.pp.41-45(PRMU), pp.41-45(SP), pp.41-45(WIT), |
| #Pages | 5 |
| Date of Issue | 2016-06-06 (PRMU, SP, WIT) |