Inducing High Performance and Compact Neural Networks Based on Decision Boundary Making

電気学会 電子図書館 Verified independent store

→

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: 2014/09/01タイトル(英語): Inducing High Performance and Compact Neural Networks Based on Decision Boundary Making著者名: Yuya Kaneda (The Universit y of Aizu), Qiangfu Zhao (The University of Aizu)著者名(英語): Yuya Kaneda (The University of Aizu), Qiangfu Zhao (The University of Aizu)キーワード: Neural Network，Support Vector Machine，Decision Boundary Learning，Decision Boundary Making要約(英語): In recent years, portable computing devices (PCDs) are becoming very popular. To improve the quality of service (QoS) for each individual user, it is necessary to develop application programs that can be aware of the user intention, preference, situation, etc., so that proper services can be recommended at proper timing. We call these kinds of programs awareness agents (A-agents). To satisfy various needs of a user, many A-agents should work together in one PCD. Since the computing resource in a PCD is limited, it is necessary to reduce the implementation costs of the A-agents while preserving their performance. For this purpose, we propose two decision boundary making (DBM) algorithms in this paper. The basic idea of DBM is to generate new training data using given ones to fit the decision boundary (DB) of the given problem, and induce small neural networks (NNs) using the new data. Both algorithms proposed here are simplified versions of the decision boundary learning (DBL) algorithm proposed by us earlier. Using the new algorithms, the cost for data generation can be greatly reduced. Experimental results show that if the new data are generated properly in positions close to the DB, the induced small NNs can perform even better than support vector machines, which are known as the state-of-the-art learning models.本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.134 No.9 （2014） 特集Ⅰ：制御系設計における適応・学習・同定・モデリングの新展開 特集Ⅱ：インテリジェント・システム本誌掲載ページ: 1299-1309 p原稿種別: 論文／英語電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/134/9/134_1299/_article/-char/ja/ Show more