ラベルの分布間距離に基づく誤り方を考慮した識別モデル

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: 2021/09/01

タイトル(英語): Classification Model Considering Misclassification Based on Distributional Distance Between Labels

著者名: 但馬　慶行（横浜国立大学 大学院 理工学府），濱上　知樹（横浜国立大学 大学院 理工学府）

著者名(英語): Yoshiyuki Tajima (Graduate School of Engineering Science, Yokohama National University), Tomoki Hamagami (Graduate School of Engineering Science, Yokohama National University)

キーワード: 深層学習，ニューラルネットワーク，識別，分布間距離　　deep learning，neural network，classification，distributional distance

要約(英語): In this study, we propose deep learning model that not only has a high accuracy, but also a small distance between training and prediction labels for unknown data in the neighbor of the training data. We define a knowledge distribution as probability distribution for each labels. The relationship between the knowledge distributions corresponds to the distance between the labels. In the proposed method, we firstly train a model to minimize distributional distance between internal features and knowledge distribution, then train the model to classify labels correctry. We visually confirmed that the proposed method can predict labels with small distance between labels for unknown data near the training data. In addition, we compared the proposed method with a existing method that uses a typical convolutional neural network. Experiments on MNIST show that the proposed method achieved the same or better accuracy than existing methods. The proposed method also achieved mean absolute error of 0.32, while the existing method achieved 0.374.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.141 No.9 （2021） 特集：知能メカトロニクス分野と連携する知覚情報技術

本誌掲載ページ: 1048-1054 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/141/9/141_1048/_article/-char/ja/