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

Self-Learning Machines Based on Hamiltonian Echo Backpropagation

Lopez-Pastor, Victor; Marquardt, Florian
Physical Review X2023-8-18DOI: 10.1103/PhysRevX.13.031020
15被引1阅读
引用收藏
分享

摘要

A physical self-learning machine can be defined as a nonlinear dynamical system that can be trained on data (similar to artificial neural networks) but where the update of the internal degrees of freedom that serve as learnable parameters happens autonomously. In this way, neither external processing and feedback nor knowledge of (and control of) these internal degrees of freedom is required. We introduce a general scheme for self-learning in any time-reversible Hamiltonian system. It relies on implementing a time-reversal operation and injecting a small error signal on top of the echo dynamics. We show how the physical dynamics itself will then lead to the required gradient update of learnable parameters, independent of the details of the Hamiltonian. We illustrate the training of such a self-learning machine numerically for the case of coupled nonlinear wave fields and other examples.

学科与关键词

关键词
NEURAL-NETWORKSARTIFICIAL-INTELLIGENCEPHASE-CONJUGATIONREPRESENTATIONSSYNAPSE
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
  • Training all-mechanical neural networks for task learning through in situ backpropagation
    Li, Shuaifeng; Mao, Xiaoming*Nature Communications, 2024, 15(1): 10528.
  • Recent advances in physical reservoir computing: A review
    Tanaka, Gouhei*; Yamane, Toshiyuki; Heroux, Jean Benoit; Nakane, Ryosho; Kanazawa, Naoki; Takeda, Seiji; Numata, Hidetoshi; Nakano, Daiju; Hirose, AkiraNeural Networks, 2019, 115: 100-123.被引 1102
查看全部 →

发表信息

论文状态
公开发表
期刊
Physical Review X
发表日期
2023-08-18
卷期
第 13 卷, 第 3 期
页码
031020
DOI
10.1103/PhysRevX.13.031020
语言
ENGLISH
成果收录
SCIE

作者

  • L

    Lopez-Pastor, Victor (第一作者)

  • M

    Marquardt, Florian

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