オチアイ　ケイヒロ   Ochiai Keihiro   落合　慶広    所属   情報経営イノベーション専門職大学  情報経営イノベーション学部 情報経営イノベーション学科    職種   准教授
言語種別	日本語
発行・発表の年月	1993/03/28
形態種別	研究論文（国際会議プロシーディングス）
査読	査読あり
標題	Improved Kick out Learning ALgorithm with Delta-Bar-Delta-Bar Rule
執筆形態	共著
掲載誌名	International Conference on Neural Networks(ICNN93,San Francisco)
掲載区分	国外
出版社・発行元	Institute of Electrical and Electronics Engineers (IEEE)
巻・号・頁	Vol.I,269-274頁
総ページ数	6
担当範囲	ほぼ全て
担当区分	筆頭著者
著者・共著者	S.Usui
概要	A new adaptive rule is proposed. It is called the delta-bar-delta-bar rule. It improves robustness for settling the increment and decrement factors of the learning rate of an accelerated backpropagation algorithm. This rule is introduced into the kick out algorithm, and it is shown that it is effective in extracting the best performance of the kick out algorithm. Using the delta-bar-delta-bar rule, the rate of convergence of the kick out algorithm is substantially improved, even though the learning rates are not optimally set.
DOI	https://doi.org/10.1109/ICNN.1993.298568
ISBN	0-7803-0999-5
PermalinkURL	https://ieeexplore.ieee.org/document/298568/authors#authors