The Ratio of the Desired Parameters of Deep Neural Networks

• ESAKI Yasushi

  Faculty of Science and Engineering, Waseda University

• NAKAHARA Yuta

  Center for Data Science, Waseda University

• MATSUSHIMA Toshiyasu

  Faculty of Science and Engineering, Waseda University

抄録

There have been some researchers that investigate the accuracy of the approximation to a function that shows a generating pattern of data by a deep neural network. However, they have confirmed only whether at least one function close to the function showing a generating pattern exists in function classes of deep neural networks whose parameter values are changing. Therefore, we propose a new criterion to infer the approximation accuracy. Our new criterion shows the existence ratio of functions close to the function showing a generating pattern in the function classes. Moreover, we show a deep neural network with a larger number of layers approximates the function showing a generating pattern more accurately than one with a smaller number of layers under the proposed criterion, with numerical simulations.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E105.A (3), 433-435, 2022-03-01

  一般社団法人 電子情報通信学会

キーワード

• neural networks
• deep learning
• the approximation accuracy of neural networks

詳細情報

• CRID: 1390573242447826816
• NII論文ID: 130008165402
• DOI: 10.1587/transfun.2021tal0003
• ISSN: 17451337
• ISSN: 09168508
• Web Site: https://www.jstage.jst.go.jp/article/transfun/E105.A/3/E105.A_2021TAL0003/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可