WEKO3
アイテム
An adaptive penalty-based learning extension for the backpropagation family
http://hdl.handle.net/2297/18073
http://hdl.handle.net/2297/18073e078ee4a-2a3e-43e7-aae8-f61f2b755359
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
TE-PR-NAKAYAMA-K-2140.pdf (324.6 kB)
|
|
| Item type | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2017-10-03 | |||||
| タイトル | ||||||
| タイトル | An adaptive penalty-based learning extension for the backpropagation family | |||||
| 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_6501 | |||||
| 資源タイプ | journal article | |||||
| 著者 |
Jansen, Boris
× Jansen, Boris× Nakayama, Kenji |
|||||
| 提供者所属 | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | 金沢大学理工研究域 電子情報学系 | |||||
| 書誌情報 |
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 巻 E89-A, 号 8, p. 2140-2148, 発行日 2006-08-01 |
|||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 0916-8508 | |||||
| NCID | ||||||
| 収録物識別子タイプ | NCID | |||||
| 収録物識別子 | AA10826239 | |||||
| DOI | ||||||
| 関連タイプ | isIdenticalTo | |||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | 10.1093/ietfec/e89-a.8.2140 | |||||
| 出版者 | ||||||
| 出版者 | Oxford University Press / 電子情報通信学会 = IEICE | |||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | Over the years, many improvements and refinements to the backpropagation learning algorithm have been reported. In this paper, a new adaptive penalty-based learning extension for the backpropagation learning algorithm and its variants is proposed. The new method initially puts pressure on artificial neural networks in order to get all outputs for all training patterns into the correct half of the output range, instead of mainly focusing on minimizing the difference between the target and actual output values. The upper bound of the penalty values is also controlled. The technique is easy to implement and computationally inexpensive. In this study, the new approach is applied to the backpropagation learning algorithm as well as the RPROP learning algorithm. The superiority of the new proposed method is demonstrated though many simulations. By applying the extension, the percentage of successful runs can be greatly increased and the average number of epochs to convergence can be well reduced on various problem instances. The behavior of the penalty values during training is also analyzed and their active role within the learning process is confirmed. Copyright © 2006 The Institute of Electronics, Information and Communication Engineers. | |||||
| 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 | |||||
| 関連URI | ||||||
| 識別子タイプ | URI | |||||
| 関連識別子 | http://www.ieice.org/eng/index.html | |||||
