Proof of the Approximation Ability of Recurrent Neural Networks to Nonlinear Continuous-Time System with Input

LI Xiao-dong; LIANG Xiao-bo

您当前的位置：

首页 >

文章列表页 >

Proof of the Approximation Ability of Recurrent Neural Networks to Nonlinear Continuous-Time System with Input

更新时间：2025-07-16

- Proof of the Approximation Ability of Recurrent Neural Networks to Nonlinear Continuous-Time System with Input
- Acta Electronica Sinica Vol. 29, Issue 1, Pages: 103-105(2001)
- 作者机构：
  
  宁夏大学物理与电气信息工程系,银川,750021
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：2001
- 稿件说明：
移动端阅览
LI Xiao-dong, LIANG Xiao-bo. Proof of the Approximation Ability of Recurrent Neural Networks to Nonlinear Continuous-Time System with Input[J]. Acta Electronica Sinica, 2001, 29(1): 103-105.
DOI：

LI Xiao-dong, LIANG Xiao-bo. Proof of the Approximation Ability of Recurrent Neural Networks to Nonlinear Continuous-Time System with Input[J]. Acta Electronica Sinica, 2001, 29(1): 103-105. DOI：

摘要

本文从多层前馈神经网络的一般近似定理出发

证明了带有输入的非线性连续系统在有限时间段内的输出轨迹可以被一类反馈神经网络输出神经元的状态向量近似到任何程度.

Abstract

Starting from the universal approximation theorem of multilayered feed forward neural networks

this paper proves that the finite time trajectory of nonlinear continuous-time system with input can be approximated by the state vector of the output units of a class of recurrent neural networks.

关键词

Keywords

references

Views

1195

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰