{"title":"Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces","authors":"M. Moghaddaszadeh, M. Mousa, A. Aref, M. Nouh","doi":"10.1063/5.0201761","DOIUrl":null,"url":null,"abstract":"The ability of mechanical systems to perform basic computations has gained traction over recent years, providing an unconventional alternative to digital computing in off grid, low power, and severe environments, which render the majority of electronic components inoperable. However, much of the work in mechanical computing has focused on logic operations via quasi-static prescribed displacements in origami, bistable, and soft deformable matter. Here, we present a first attempt to describe the fundamental framework of an elastic neuromorphic metasurface that performs distinct classification tasks, providing a new set of challenges, given the complex nature of elastic waves with respect to scattering and manipulation. Multiple layers of reconfigurable waveguides are phase-trained via constant weights and trainable activation functions in a manner that enables the resultant wave scattering at the readout location to focus on the correct class within the detection plane. We further demonstrate the neuromorphic system’s reconfigurability in performing two distinct tasks, eliminating the need for costly remanufacturing.","PeriodicalId":7985,"journal":{"name":"APL Materials","volume":null,"pages":null},"PeriodicalIF":5.3000,"publicationDate":"2024-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"APL Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1063/5.0201761","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The ability of mechanical systems to perform basic computations has gained traction over recent years, providing an unconventional alternative to digital computing in off grid, low power, and severe environments, which render the majority of electronic components inoperable. However, much of the work in mechanical computing has focused on logic operations via quasi-static prescribed displacements in origami, bistable, and soft deformable matter. Here, we present a first attempt to describe the fundamental framework of an elastic neuromorphic metasurface that performs distinct classification tasks, providing a new set of challenges, given the complex nature of elastic waves with respect to scattering and manipulation. Multiple layers of reconfigurable waveguides are phase-trained via constant weights and trainable activation functions in a manner that enables the resultant wave scattering at the readout location to focus on the correct class within the detection plane. We further demonstrate the neuromorphic system’s reconfigurability in performing two distinct tasks, eliminating the need for costly remanufacturing.
期刊介绍:
APL Materials features original, experimental research on significant topical issues within the field of materials science. In order to highlight research at the forefront of materials science, emphasis is given to the quality and timeliness of the work. The journal considers theory or calculation when the work is particularly timely and relevant to applications.
In addition to regular articles, the journal also publishes Special Topics, which report on cutting-edge areas in materials science, such as Perovskite Solar Cells, 2D Materials, and Beyond Lithium Ion Batteries.