ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Training all-mechanical neural networks for task learning through in situ backpropagation

Li, Shuaifeng; Mao, Xiaoming*
Nature Communications2024-12-9DOI: 10.1038/s41467-024-54849-z
1阅读
引用收藏
分享

摘要

Recent advances unveiled physical neural networks as promising machine learning platforms, offering faster and more energy-efficient information processing. Compared with extensively-studied optical neural networks, the development of mechanical neural networks remains nascent and faces significant challenges, including heavy computational demands and learning with approximate gradients. Here, we introduce the mechanical analogue of in situ backpropagation to enable highly efficient training of mechanical neural networks. We theoretically prove that the exact gradient can be obtained locally, enabling learning through the immediate vicinity, and we experimentally demonstrate this backpropagation to obtain gradient with high precision. With the gradient information, we showcase the successful training of networks in simulations for behavior learning and machine learning tasks, achieving high accuracy in experiments of regression and classification. Furthermore, we present the retrainability of networks involving task-switching and damage, demonstrating the resilience. Our findings, which integrate the theory for training mechanical neural networks and experimental and numerical validations, pave the way for mechanical machine learning hardware and autonomous self-learning material systems.

学科与关键词

关键词
ARTIFICIAL-INTELLIGENCEROBUSTNESS
相关
加载中…
  • LearningWithout Neurons in Physical Systems
    Stern, Menachem*; Murugan, ArvindAnnual Review of Condensed Matter Physics, 2023, 14: 417-441.被引 26
  • Self-Learning Machines Based on Hamiltonian Echo Backpropagation
    Lopez-Pastor, Victor; Marquardt, FlorianPhysical Review X, 2023, 13(3): 031020.被引 15
  • Fully forward mode training for optical neural networks
    Xue, Zhiwei; Zhou, Tiankuang; Xu, Zhihao; Yu, Shaoliang; Dai, Qionghai*; Fang, Lu*Nature, 2024, 632(8024).被引 2
查看全部 →

发表信息

论文状态
公开发表
期刊
Nature Communications
发表日期
2024-12-09
卷期
第 15 卷, 第 1 期
页码
10528
DOI
10.1038/s41467-024-54849-z
语言
ENGLISH
成果收录
SCIE
资助标注
Office of Naval Research(MURI N00014-20-1-2479) and National Science Foundation Center for Complex Particle Systems(Award #2243104) [MURI N00014-20-1-2479]; Office of Naval Research [2243104]; National Science Foundation Center for Complex Particle Systems

作者

  • L

    Li, Shuaifeng (第一作者)

  • M

    Mao, Xiaoming (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417