応用プロトタイプによるオンライン実習型ディープラーニング教育方式とその実践評価

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: 2023/06/01

タイトル(英語): Practical Deep Learning Education Method by building Applied Prototypes and its Practical Evaluation

著者名: 大高　謙二（NPO法人M2M・IoT研究会），清尾　克彦（サイバー大学），大江　信宏（サイバー大学），澤本　潤（NPO法人M2M・IoT研究会），井上　雅裕（慶應義塾大学大学院システムデザイン・マネジメント研究科），小泉　寿男（NPO法人M2M・IoT研究会）

著者名(英語): Kenji Ohtaka (NPO Organization M2M・IoT Study Group), Katsuhiko Seo (Cyber University), Nobuhiro Ooe (Cyber University), Jun Sawamoto (NPO Organization M2M・IoT Study Group), Masahiro Inoue (Graduate School of System Design and Management, Keio University),

キーワード: AI，ディープラーニング，CNN，機械学習，異常検出，教育手法　　AI，deep learning，CNN，machine learning，anomaly detection，education method

要約(英語): In deep learning (hereinafter referred to as DL) education, universities, research institutes and large companies are promoting education by fostering educators and creating curriculums based on national policies. However, especially small and medium-sized enterprises and companies in industries that are not good at IT cannot prepare their own educational environment, and it is considered that the educational environment for improving the added value of products and services by DL is not sufficient. Furthermore, the neural network, which is a component of DL, has a feature that it is difficult to determine the feasibility for the realization target. This feature is an issue in educational methods. Based on the above situation, we proposed an educational method that combines online live lectures, reviews, and homework as DL applied education, and confirmed its practice and educational effect.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.143 No.6 （2023）

本誌掲載ページ: 597-607 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/143/6/143_597/_article/-char/ja/