Ensemble of Single-Layered Complex-Valued Neural Networks for Classification Tasks

• 資料種別: 文書・図像類
• タイトル: Ensemble of Single-Layered Complex-Valued Neural Networks for Classification Tasks
• 著者・編者: AMIN, Md. Faijul; ISLAM, Md. Monirul; MURASE, Kazuyuki
• 著者標目: AMIN, Md. Faijul; ISLAM, Md. Monirul; MURASE, Kazuyuki
• 出版事項: ELSEVIER SCIENCE B.V.
• 出版年月日等: 2009-06
• 出版年（W3CDTF）: 2009-06
• タイトル（掲載誌）: Neurocomputing
• 巻号年月日等（掲載誌）: 72 10-12
• 掲載巻: 72
• 掲載号: 10-12
• 掲載ページ: 2227-2234
• 本文の言語コード: eng
• 件名標目: activation function; classification; complex-valued neural network; ensemble
• 対象利用者: 一般
• 一般注記: This paper presents ensemble approaches in single-layered complex-valued neural network (CVNN) to solve real-valued classification problems. Each component CVNN of an ensemble uses a recently proposed activation function for its complex-valued neurons (CVNs). A gradient-descent based learning algorithm was used to train the component CVNNs. We applied two ensemble methods, negative correlation learning and bagging, to create the ensembles. Experimental results on a number of real-world benchmark problems showed a substantial performance improvement of the ensembles over the individual single-layered CVNN classifiers. Furthermore, the generalization performances were nearly equivalent to those obtained by the ensembles of real-valued multilayer neural networks.
• 一次資料へのリンクURL: https://u-fukui.repo.nii.ac.jp/?action=repository_action_common_download&item_id=22619&item_no=1&attribute_id=22&file_no=1
• オンライン閲覧公開範囲: 限定公開
• 関連情報（DOI）: 10.1016/j.neucom.2008.12.028
• 連携機関・データベース: 国立情報学研究所 : 学術機関リポジトリデータベース（IRDB）（機関リポジトリ）; https://irdb.nii.ac.jp
• 提供元機関・データベース: 福井大学 : 福井大学学術機関リポジトリ