Approximation of dynamical time-variant systems by continuous-time recurrent neural networks

被引：73

作者：

Li, XD ^{[1
]}

Ho, JKL

Chow, TWS

机构：

[1] City Univ Hong Kong, Dept Mfg Engn & Engn Management, Hong Kong, Hong Kong, Peoples R China

[2] Sun Yat Sen Univ, Dept Elect Engn, Guangzhou, Guangdong, Peoples R China

[3] City Univ Hong Kong, Dept Elect Engn, Hong Kong, Hong Kong, Peoples R China

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS | 2005年 / 52卷 / 10期

关键词：

approximation; dynamical time-variant systems; recurrent neural networks;

D O I：

10.1109/TCSII.2005.852006

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This paper studies the approximation ability of continuous-time recurrent neural networks to dynamical time-variant systems. It proves that any finite time trajectory of a given dynamical time-variant system can be approximated by the internal state of a continuous-time recurrent neural network. Given several special forms of dynamical time-variant systems or trajectories, this paper shows that they can all be approximately realized by the internal state of a simple recurrent neural network.

引用

页码：656 / 660

页数：5

共 50 条

[1] APPROXIMATION OF DYNAMICAL-SYSTEMS BY CONTINUOUS-TIME RECURRENT NEURAL NETWORKS
FUNAHASHI, K
NAKAMURA, Y
[J]. NEURAL NETWORKS, 1993, 6 (06) : 801 - 806
[2] Approximation of recurrent neural networks to nonlinear time-variant discrete systems
Li, Xiao-Dong
Yang, Guo-Hua
[J]. Zhongshan Daxue Xuebao/Acta Scientiarum Natralium Universitatis Sunyatseni, 2002, 41 (05):
[3] On unique representations of certain dynamical systems produced by continuous-time recurrent neural networks
Kimura, M
[J]. NEURAL COMPUTATION, 2002, 14 (12) : 2981 - 2996
[4] Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks
Li, Zhong
Han, Jiequn
Weinan, E.
Li, Qianxiao
[J]. Journal of Machine Learning Research, 2022, 23
[5] Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks
Li, Zhong
Han, Jiequn
E, Weinan
Li, Qianxiao
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23 : 1 - 85
[6] Approximation Capability of Continuous Time Recurrent Neural Networks for Non-autonomous Dynamical Systems
Nakamura, Yuichi
Nakagawa, Masahiro
[J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2009, PT II, 2009, 5769 : 593 - 602
[7] Continuous-Time Signal Processing with Time-Variant Delay
Sotiriadis, Paul P.
Adams, Robert
[J]. ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5, 2009, : 457 - +
[8] Modeling of continuous time dynamical systems with input by recurrent neural networks
Chow, TWS
Li, XD
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2000, 47 (04): : 575 - 578
[9] ON THE DYNAMICS OF SMALL CONTINUOUS-TIME RECURRENT NEURAL NETWORKS
BEER, RD
[J]. ADAPTIVE BEHAVIOR, 1995, 3 (04) : 469 - 509
[10] A learning result for continuous-time recurrent neural networks
Sontag, ED
[J]. SYSTEMS & CONTROL LETTERS, 1998, 34 (03) : 151 - 158

← 1 2 3 4 5 →