• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

通过时间偏移来减小储层计算机的规模。

Time shifts to reduce the size of reservoir computers.

作者信息

Carroll Thomas L, Hart Joseph D

机构信息

U.S. Naval Research Laboratory, Washington D.C. 20375, USA.

出版信息

Chaos. 2022 Aug;32(8):083122. doi: 10.1063/5.0097850.

DOI:10.1063/5.0097850
PMID:36049918
Abstract

A reservoir computer is a type of dynamical system arranged to do computation. Typically, a reservoir computer is constructed by connecting a large number of nonlinear nodes in a network that includes recurrent connections. In order to achieve accurate results, the reservoir usually contains hundreds to thousands of nodes. This high dimensionality makes it difficult to analyze the reservoir computer using tools from the dynamical systems theory. Additionally, the need to create and connect large numbers of nonlinear nodes makes it difficult to design and build analog reservoir computers that can be faster and consume less power than digital reservoir computers. We demonstrate here that a reservoir computer may be divided into two parts: a small set of nonlinear nodes (the reservoir) and a separate set of time-shifted reservoir output signals. The time-shifted output signals serve to increase the rank and memory of the reservoir computer, and the set of nonlinear nodes may create an embedding of the input dynamical system. We use this time-shifting technique to obtain excellent performance from an opto-electronic delay-based reservoir computer with only a small number of virtual nodes. Because only a few nonlinear nodes are required, construction of a reservoir computer becomes much easier, and delay-based reservoir computers can operate at much higher speeds.

摘要

储层计算机是一种用于进行计算的动力系统。通常,储层计算机通过在包含递归连接的网络中连接大量非线性节点来构建。为了获得准确的结果,储层通常包含数百到数千个节点。这种高维度使得使用动力系统理论工具分析储层计算机变得困难。此外,创建和连接大量非线性节点的需求使得设计和构建比数字储层计算机更快且功耗更低的模拟储层计算机变得困难。我们在此证明,储层计算机可分为两部分:一小部分非线性节点(储层)和一组单独的经时移的储层输出信号。经时移的输出信号用于增加储层计算机的秩和记忆,并且该组非线性节点可以创建输入动力系统的嵌入。我们使用这种时移技术从仅具有少量虚拟节点的基于光电延迟的储层计算机中获得了优异的性能。由于只需要少数非线性节点,储层计算机 的构建变得容易得多,并且基于延迟的储层计算机可以以更高的速度运行。

相似文献

1
Time shifts to reduce the size of reservoir computers.通过时间偏移来减小储层计算机的规模。
Chaos. 2022 Aug;32(8):083122. doi: 10.1063/5.0097850.
2
Network structure effects in reservoir computers.储层计算机中的网络结构效应
Chaos. 2019 Aug;29(8):083130. doi: 10.1063/1.5097686.
3
Optimizing memory in reservoir computers.优化储层计算机中的记忆
Chaos. 2022 Feb;32(2):023123. doi: 10.1063/5.0078151.
4
Optimizing Reservoir Computers for Signal Classification.优化用于信号分类的储层计算机。
Front Physiol. 2021 Jun 18;12:685121. doi: 10.3389/fphys.2021.685121. eCollection 2021.
5
Low dimensional manifolds in reservoir computers.储层计算机中的低维流形
Chaos. 2021 Apr;31(4):043113. doi: 10.1063/5.0047006.
6
Path length statistics in reservoir computers.水库计算机中的路径长度统计
Chaos. 2020 Aug;30(8):083130. doi: 10.1063/5.0014643.
7
All-optical reservoir computer based on saturation of absorption.基于吸收饱和的全光储层计算机。
Opt Express. 2014 May 5;22(9):10868-81. doi: 10.1364/OE.22.010868.
8
Time-shift selection for reservoir computing using a rank-revealing QR algorithm.使用秩揭示 QR 算法的储层计算的时移选择。
Chaos. 2023 Apr 1;33(4). doi: 10.1063/5.0141251.
9
Dimension of reservoir computers.储层计算机的维度。
Chaos. 2020 Jan;30(1):013102. doi: 10.1063/1.5128898.
10
Boosting reservoir computer performance with multiple delays.通过多重延迟提升储层计算机性能。
Phys Rev E. 2024 May;109(5-1):054203. doi: 10.1103/PhysRevE.109.054203.

引用本文的文献

1
Optomechanical reservoir computing.光机械储能计算
Proc Natl Acad Sci U S A. 2025 Jul 22;122(29):e2424991122. doi: 10.1073/pnas.2424991122. Epub 2025 Jul 14.
2
Post-processing methods for delay embedding and feature scaling of reservoir computers.用于水库计算机延迟嵌入和特征缩放的后处理方法。
Commun Eng. 2025 Jan 27;4(1):10. doi: 10.1038/s44172-024-00330-0.
3
Synchronizing chaos using reservoir computing.使用回声状态网络同步混沌现象。
Chaos. 2023 Oct 1;33(10). doi: 10.1063/5.0161076.