首页    期刊浏览 2024年12月03日 星期二
登录注册

文章基本信息

  • 标题:Supervised learning through physical changes in a mechanical system
  • 本地全文:下载
  • 作者:Menachem Stern ; Chukwunonso Arinze ; Leron Perez
  • 期刊名称:Proceedings of the National Academy of Sciences
  • 印刷版ISSN:0027-8424
  • 电子版ISSN:1091-6490
  • 出版年度:2020
  • 卷号:117
  • 期号:26
  • 页码:14843-14850
  • DOI:10.1073/pnas.2000807117
  • 出版社:The National Academy of Sciences of the United States of America
  • 摘要:Mechanical metamaterials are usually designed to show desired responses to prescribed forces. In some applications, the desired force–response relationship is hard to specify exactly, but examples of forces and desired responses are easily available. Here, we propose a framework for supervised learning in thin, creased sheets that learn the desired force–response behavior by physically experiencing training examples and then, crucially, respond correctly (generalize) to previously unseen test forces. During training, we fold the sheet using training forces, prompting local crease stiffnesses to change in proportion to their experienced strain. We find that this learning process reshapes nonlinearities inherent in folding a sheet so as to show the correct response for previously unseen test forces. We show the relationship between training error, test error, and sheet size (model complexity) in learning sheets and compare them to counterparts in machine-learning algorithms. Our framework shows how the rugged energy landscape of disordered mechanical materials can be sculpted to show desired force–response behaviors by a local physical learning process.
  • 关键词:physical learning ; supervised learning ; adaptation ; origami ; metamaterials
国家哲学社会科学文献中心版权所有