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

Universality and Approximation Bounds for Echo State Networks With Random Weights

Li, Zhen; Yang, Yunfei*香港城市大学
IEEE Transactions on Neural Networks and Learning Systems2023-12-13DOI: 10.1109/TNNLS.2023.3339512
11阅读
引用收藏
分享

摘要

We study the uniform approximation of echo state networks (ESNs) with randomly generated internal weights. These models, in which only the readout weights are optimized during training, have made empirical success in learning dynamical systems. Recent results showed that ESNs with ReLU activation are universal. In this article, we give an alternative construction and prove that the universality holds for general activation functions. Specifically, our main result shows that, under certain condition on the activation function, there exists a sampling procedure for the internal weights so that the ESN can approximate any continuous casual time-invariant operators with high probability. In particular, for ReLU activation, we give explicit construction for these sampling procedures. We also quantify the approximation error of the constructed ReLU ESNs for sufficiently regular operators.

学科与关键词

关键词
Approximation errorecho state networks (ESNs)reservoir computinguniversality
相关
加载中…
  • Determining Reservoir Topologies from Short-Term Memory in Echo State Networks
    Qianli, Ma; Weibiao, ChenCommunications in Computer and Information Science, Springer Berlin Heidelberg, 64-71, 2012.
  • How neural networks work: Unraveling the mystery of randomized neural networks for functions and chaotic dynamical systems
    Bollt, Erik*Chaos, 2024, 34(12): 123164.
  • Design of sparse Bayesian echo state network for time series prediction
    Wang, Lei*; Su, Zhong; Qiao, Junfei; Yang, CuiliNEURAL COMPUTING & APPLICATIONS, 2021, 33(12): 7089-7102.被引 5
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Neural Networks and Learning Systems
发表日期
2023-12-13
DOI
10.1109/TNNLS.2023.3339512
语言
ENGLISH
成果收录
SCIE

作者

  • L

    Li, Zhen (第一作者)

  • Y

    Yang, Yunfei (通讯)

    hong kong univ sci & technol · city univ hong kong

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