DSpace width= university logo mark
Japanese | English 

KURA > B. 理工学域・研究域/理工学部/自然科学研究科 > b10. 学術雑誌掲載論文 > 1.査読済論文(工) >

全文を表示する

ファイル 記述 サイズフォーマット
TE-PR-NAKAYAMA-K-374.pdf641.77 kBAdobe PDF
見る/開く
タイトル: Training data selection method for generalization by multilayer neural networks
著者: Hara, Kazuyuki
Nakayama, Kenji link image
中山, 謙二
発行日: 1998年 3月
雑誌名: IEICE Trans. Fundamentals
ISSN: 0916-8508
巻: E81-A
号: 3
開始ページ: 374
終了ページ: 381
抄録: A training data selection method is proposed for multilayer neural networks (MLNNs). This method selects a small number of the training data, which guarantee both generalization and fast training of the MLNNs applied to pattern classification. The generalization will be satisfied using the data locate close to the boundary of the pattern classes. However, if these data are only used in the training, convergence is slow. This phenomenon is analyzed in this paper. Therefore, in the proposed method, the MLNN is first trained using some number of the data, which are randomly selected (Step 1). The data, for which the output error is relatively large, are selected. Furthermore, they are paired with the nearest data belong to the different class. The newly selected data are further paired with the nearest data. Finally, pairs of the data, which locate close to the boundary, can be found. Using these pairs of the data, the MLNNs are further trained (Step 2). Since, there are some variations to combine Steps 1 and 2, the proposed method can be applied to both off-line and on-line training. The proposed method can reduce the number of the training data, at the same time, can hasten the training. Usefulness is confirmed through computer simulation.
URI: http://hdl.handle.net/2297/5654
資料種別: Journal Article
権利関係: (社)電子情報通信学会の許諾を得て登録
版表示: publisher
出現コレクション:1.査読済論文(工)

このアイテムを引用あるいはリンクする場合は次の識別子を使用してください。 http://hdl.handle.net/2297/5654

本リポジトリに保管されているアイテムはすべて著作権により保護されています。

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - ご意見をお寄せください