WEKO3
インデックスリンク
アイテム
A hybrid learning algorithm for multilayer perceptrons to improve generalization under sparse training data conditions
http://hdl.handle.net/2297/6847
http://hdl.handle.net/2297/6847de8f285f-c96d-4563-96ad-572166016a67
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
TE-PR-NAKAYAMA-K-967.pdf (158.9 kB)
|
|
| Item type | 会議発表論文 / Conference Paper(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2017-10-03 | |||||
| タイトル | ||||||
| タイトル | A hybrid learning algorithm for multilayer perceptrons to improve generalization under sparse training data conditions | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
| 資源タイプ | conference paper | |||||
| 著者 |
Tonomura, M.
× Tonomura, M.× Nakayama, Kenji |
|||||
| 書誌情報 |
IEEE&INNS, Proc. IJCNN'2001, Washington DC 巻 2, p. 967-972, 発行日 2001-07-01 |
|||||
| 出版者 | ||||||
| 出版者 | IEEE(Institute of Electrical and Electronics Engineers) | |||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | The back-propagation algorithm is mainly used for multilayer perceptrons. This algorithm is, however, difficult to achieve high generalization when the number of training data is limited, that is sparse training data. In this paper, a new learning algorithm is proposed. It combines the BP algorithm and modifies hyperplanes taking internal information into account. In other words, the hyperplanes are controlled by the distance between the hyperplanes and the critical training data, which locate close to the boundary. This algorithm works well for the sparse training data to achieve high generalization. In order to evaluate generalization, it is supposed that all data are normally distributed around the training data. Several simulations of pattern classification demonstrate efficiency of the proposed. | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
