<テクニカルレポート>
Learning of Three-Layered Neural Networks by Enlarging Domains of Recognition

作成者
本文言語
出版者
発行日
雑誌名
出版タイプ
アクセス権
概要 The concept of domains of recognition is introduced for three-layered neural networks. The domain lies in the input space and can be represented using connection weights and thresholds of the network.... We propose a learning method of the network so as to enlarge the domain of recognition by extending its range mapped into the hidden space and by minimizing the slope of affine transforms in the mapping. Based on the method, we introduce a cost function whose minimization process gives a learning algorithm of the network. A land cover classification problem has been considered in our simulation.続きを見る

本文情報を非表示

trcs172.ps gz 923 KB 23  
trcs172 pdf 365 KB 39  

詳細

レコードID
査読有無
関連情報
関連情報
タイプ
登録日 2009.04.22
更新日 2017.01.20