講演名 2008-08-04
A Hybrid PSO and quasi-Newton Technique for Training of Feedforward Neural Networks
,
PDFダウンロードページ PDFダウンロードページへ
抄録(和)
抄録(英) This paper describes a new technique for training feedforward neural networks. We employ the proposed algorithm for robust neural network training purpose. Conventional neural network training algorithms based on the gradient descent often encounter local minima problems. Recently, some evolutionary algorithms are getting a lot more attention about global search ability but are less-accurate for complicated training task of neural networks. The proposed technique hybridizes local training algorithm based on quasi-Newton method with a recent global optimization algorithm called Particle Swarm Optimization (PSO). The proposed technique provides higher global convergence property than the conventional global optimization technique. Neural network training for some benchmark problems is presented to demonstrate the proposed algorithm. The proposed algorithm achieves more accurate and robust training results than the quasi-Newton method and the conventional PSOs.
キーワード(和)
キーワード(英) Feedforward neural networks / Particle swarm optimization / quasi-Newton method / Hybrid algorithm
資料番号 CST2008-17
発行日

研究会情報
研究会 CST
開催期間 2008/7/28(から1日開催)
開催地(和)
開催地(英)
テーマ(和)
テーマ(英)
委員長氏名(和)
委員長氏名(英)
副委員長氏名(和)
副委員長氏名(英)
幹事氏名(和)
幹事氏名(英)
幹事補佐氏名(和)
幹事補佐氏名(英)

講演論文情報詳細
申込み研究会 Concurrent System Technology (CST)
本文の言語 ENG
タイトル(和)
サブタイトル(和)
タイトル(英) A Hybrid PSO and quasi-Newton Technique for Training of Feedforward Neural Networks
サブタイトル(和)
キーワード(1)(和/英) / Feedforward neural networks
第 1 著者 氏名(和/英) / Hiroshi NINOMIYA
第 1 著者 所属(和/英)
Department of Information Science, Shonan Institute of Technology
発表年月日 2008-08-04
資料番号 CST2008-17
巻番号(vol) vol.108
号番号(no) 176
ページ範囲 pp.-
ページ数 6
発行日