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	1992
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	New　Accelerated Learning　Algorithm to Reduce the Oscillation of Weights in Multilayered Neural Networks
執筆形態	共著
掲載誌名	International Joint Conference on Neural Networks(IJCNN92,Batimore)
掲載区分	国外
出版社・発行元	Institute of Electrical and Electronics Engineers (IEEE)
巻・号・頁	Vol.1,914-919頁
担当範囲	全て
担当区分	筆頭著者
著者・共著者	Toda Naohiro, Usui Shiro
概要	An accelerated learning algorithm is proposed. It is based on R.A. Jacob's heuristics with reduction of the oscillation by correcting the next point of weight to the bottom of a ravine. The performance is evaluated through several simulation examples and compared with several acceleration algorithms, such as the DBD (delta-bar-delta) algorithm and the EDBD (extended delta-bar-delta) algorithm. Simulation results showed that the proposed algorithm converges 3.7 times faster than the DBD algorithm, 1.8 times faster than the EDBD algorithm, and 19.4 times faster than the basic backpropagation.
DOI	https://doi.org/10.1109/IJCNN.1992.287070
ISBN	0-7803-0559-0
PermalinkURL	https://ieeexplore.ieee.org/abstract/document/287070