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

• Material Type: 文書・図像類
• Title: Ensemble of Single-Layered Complex-Valued Neural Networks for Classification Tasks
• Author/Editor: AMIN, Md. Faijul; ISLAM, Md. Monirul; MURASE, Kazuyuki
• Author Heading: AMIN, Md. Faijul; ISLAM, Md. Monirul; MURASE, Kazuyuki
• Publication, Distribution, etc.: ELSEVIER SCIENCE B.V.
• Publication Date: 2009-06
• Publication Date (W3CDTF): 2009-06
• Periodical title: Neurocomputing
• No. or year of volume/issue: 72 10-12
• Volume: 72
• Issue: 10-12
• Pages: 2227-2234
• Text Language Code: eng
• Subject Heading: activation function; classification; complex-valued neural network; ensemble
• Target Audience: 一般
• Note (General): 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.
• Source: https://u-fukui.repo.nii.ac.jp/?action=repository_action_common_download&item_id=22619&item_no=1&attribute_id=22&file_no=1
• Access Restrictions: 限定公開
• Related Material (DOI): 10.1016/j.neucom.2008.12.028
• Data Provider (Database): 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
• Original Data Provider (Database): 福井大学 : 福井大学学術機関リポジトリ