WEKO3
インデックスリンク
アイテム
H_∞-Learning of Layered Neural Networks
https://iwate-u.repo.nii.ac.jp/records/9940
https://iwate-u.repo.nii.ac.jp/records/994004270e09-3316-49c9-89c4-f77f4687be3f
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
itnn-v12n6p1265-1277.pdf (391.3 kB)
|
|
| Item type | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2010-08-02 | |||||
| タイトル | ||||||
| タイトル | H_∞-Learning of Layered Neural Networks | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | Backpropagation | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | H_∞ filter | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | H_∞-learning | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | Kalman filter | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | learning algorithm | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | neural network | |||||
| キーワード | ||||||
| 主題Scheme | Other | |||||
| 主題 | robust estimation | |||||
| 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 |
NISHIYAMA, Kiyoshi
× NISHIYAMA, Kiyoshi× SUZUKI, Kiyohiko |
|||||
| 著者(機関) | ||||||
| 値 | Department of Computer and Information Science, Faculty of Engineering, Iwate University | |||||
| 登録日 | ||||||
| 日付 | 2010-08-02 | |||||
| 書誌情報 |
IEEE Transactions on Neural Networks 巻 12, 号 6, p. 1265-1277, 発行日 2001-11-01 |
|||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 1045-9227 | |||||
| Abstract | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | Although the backpropagation (BP) scheme is widely used as a learning algorithm for multilayered neural networks, the learning speed of the BP algorithm to obtain acceptable errors is unsatisfactory in spite of some improvements such as introduction of a momentum factor and an adaptive learning rate in the weight adjustment. To solve this problem, a fast learning algorithm based on the extended Kalman filter (EKF) is presented and fortunately its computational complexity has been reduced by some simplifications. In general, however, the Kalman filtering algorithm is well known to be sensitive to the nature of noises which is generally assumed to be Gaussian. In addition, the H_∞ theory suggests that the maximum energy gain of the Kalman algorithm from disturbances to the estimation error has no upper bound. Therefore, the EKF-based learning algorithms should be improved to enhance the robustness to variations in the initial values of link weights and thresholds as well as to the nature of noises. The paper proposes H_∞-learning as a novel learning rule and to derive new globally and locally optimized learning algorithms based on H_∞-learning. Their learning behavior is analyzed from various points of view using computer simulations. The derived algorithms are also compared, in performance and computational cost, with the conventional BP and EKF learning algorithms. | |||||
| 出版者 | ||||||
| 出版者 | IEEE | |||||
| 権利 | ||||||
| 権利情報 | copyright © 2001 IEEE | |||||
| DOI | ||||||
| 関連タイプ | isIdenticalTo | |||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | 10.1109/72.963763 | |||||
| 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 | |||||
