画像認識のための階層型ニューラルネットワークの進化的構造最適化

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: 2011/05/01

タイトル(英語): Evolutionary Structure Optimization of Hierarchical Neural Network for Image Recognition

著者名: 鈴木　聡（東京農工大学），満倉　靖恵（東京農工大学）

著者名(英語): Satoru Suzuki (Tokyo University of Agriculture and Technology), Yasue Mitsukura (Tokyo University of Agriculture and Technology)

キーワード: ニューラルネットワーク，遺伝的アルゴリズム，顔認識，テクスチャ分類　　Neural Network，Genetic Algorithm，Face Recognition，Texture Classification

要約(英語): The purpose of this paper is to optimize the structure of hierarchical neural network. In this paper, structure optimization is to represent neural network by minimum number of nodes and connections, and is performed by eliminating unnecessary connections from trained neural network by using genetic algorithm. We focus on the neural network which specialized for image recognition problems. The flow of the proposed method is as follows. Firstly, walsh-hadamard transform is applied to images for feature extraction. Secondly, neural network is trained with extracted features based on back-propagation algorithm. After neural network training, unnecessary connections are eliminated from trained neural network by utilizing genetic algorithm. Finally, neural network is retrained to recover the degradation caused by connection elimination. In order to validate the usefulness of the proposed method, face recognition and texture classification examples are used. From the experimental results, it was shown that compact neural network was generated, keeping generalization performance by proposed method.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.131 No.5 （2011） 特集：メタヒューリスティクスとその応用

本誌掲載ページ: 983-989 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/131/5/131_5_983/_article/-char/ja/