Evolutionary structure optimization of hierarchical neural network for image recognition

Satoru Suzuki, Yasue Mitsukura

研究成果: Article査読

抄録

The purpose of this paper is to optimize the structure of hierarchical neural network (NN). In our proposed method, the structure optimization is considered as combinatorial optimization problem, and unnecessary connections in trained NN are eliminated by using genetic algorithm (GA).We focus on the NN which specialized for image recognition problems. 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.

本文言語English
ページ(範囲)983-989
ページ数7
ジャーナルIEEJ Transactions on Electronics, Information and Systems
131
5
DOI
出版ステータスPublished - 2011
外部発表はい

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

フィンガープリント 「Evolutionary structure optimization of hierarchical neural network for image recognition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル