相互結合型ネットワークにおけるメタヒューリスティクスを用いた動的想起

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2011/08/01

タイトル(英語): The Dynamical Recollection of Interconnected Neural Networks Using Meta-heuristics

著者名: 呉本　尭（山口大学大学院理工学研究科），渡邊　駿（山口大学大学院理工学研究科），小林　邦和（山口大学大学院理工学研究科），馮　良炳（山口大学大学院理工学研究科），大林　正直（山口大学大学院理工学研究科）

著者名(英語): Takashi Kuremoto (Graduate School of Science and Engineering, Yamaguchi University), Shun Watanabe (Graduate School of Science and Engineering, Yamaguchi University), Kunikazu Kobayashi (Graduate School of Science and Engineering, Yamaguchi University), Laing-Bing Feng (Graduate School of Science and Engineering, Yamaguchi University), Masanao Obayashi (Graduate School of Science and Engineering, Yamaguchi University)

キーワード: カオスニューラルネットワーク，ホップフィールドネットワーク，粒子群最適化，遺伝的アルゴリズム　　chaotic neural network，Hopfield network，particle swarm optimization，genetic algorithm

要約(英語): The interconnected recurrent neural networks are well-known with their abilities of associative memory of characteristic patterns. For example, the traditional Hopfield network (HN) can recall stored pattern stably, meanwhile, Aihara's chaotic neural network (CNN) is able to realize dynamical recollection of a sequence of patterns. In this paper, we propose to use meta-heuristic (MH) methods such as the particle swarm optimization (PSO) and the genetic algorithm (GA) to improve traditional associative memory systems. Using PSO or GA, for CNN, optimal parameters are found to accelerate the recollection process and raise the rate of successful recollection, and for HN, optimized bias current is calculated to improve the network with dynamical association of a series of patterns. Simulation results of binary pattern association showed effectiveness of the proposed methods.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.131 No.8 （2011）

本誌掲載ページ: 1475-1484 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/131/8/131_8_1475/_article/-char/ja/