Robust local stability of multilayer recurrent neural networks

被引：40

作者：

Suykens, JAK ^{[1
]}

De Moor, B ^{[1
]}

Vandewalle, J ^{[1
]}

机构：

[1] Katholieke Univ Leuven, Dept Elect Engn, ESAT SISTA, B-3001 Heverlee, Belgium

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2000年 / 11卷 / 01期

关键词：

dynamic backpropagation; linearization; matrix inequalities; NLq theory;

D O I：

10.1109/72.822525

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper we derive a condition for robust local stability of multilayer recurrent neural networks with two hidden layers, The stability condition follows from linking theory about linearization, robustness analysis of linear systems under nonlinear perturbation and matrix inequalities. A characterization of the basin of attraction of the origin is given in terms of the level set of a quadratic Lyapunov function. In a similar way like for NLq theory, local stability is imposed around the origin and the apparent basin of attraction is made large by applying the criterion, while the proven basin of attraction is relatively small due to conservatism of the criterion. Modifying dynamic backpropagation by the new stability condition is discussed and illustrated by simulation examples.

引用

页码：222 / 229

页数：8

共 50 条

[1] Multilayer recurrent neural networks for online robust pole assignment
Hu, SQ
Wang, J
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS, 2003, 50 (11): : 1488 - 1494
[2] Global robust stability of delayed recurrent neural networks
Cao, JD
Huang, DS
Qu, YZ
CHAOS SOLITONS & FRACTALS, 2005, 23 (01) : 221 - 229
[3] Multilayer recurrent neural networks
Kwan, HK
2002 45TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL III, CONFERENCE PROCEEDINGS, 2002, : 97 - 100
[4] Robust stability of recurrent neural networks with ISS learning algorithm
Ahn, Choon Ki
NONLINEAR DYNAMICS, 2011, 65 (04) : 413 - 419
[5] Robust stability of recurrent neural networks with ISS learning algorithm
Choon Ki Ahn
Nonlinear Dynamics, 2011, 65 : 413 - 419
[6] Stability analysis of discrete-time recurrent multilayer neural networks
Barabanov, NE
Prokhorov, DV
2004 43RD IEEE CONFERENCE ON DECISION AND CONTROL (CDC), VOLS 1-5, 2004, : 4958 - 4963
[7] Absolute stability and dissipativity of continuous time multilayer recurrent neural networks
Suykens, JAK
Vandewalle, J
ISCAS '97 - PROCEEDINGS OF 1997 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS I - IV: CIRCUITS AND SYSTEMS IN THE INFORMATION AGE, 1997, : 517 - 520
[8] Robust stability and robust periodicity of delayed recurrent neural networks with noise disturbance
Li, Chunguang
Liao, Xiaofeng
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2006, 53 (10) : 2265 - 2273
[9] Multilayer recurrent neural networks for real-time robust pole assignment
Hu, SQ
Wang, J
ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 1104 - 1108
[10] Robust global stability of discrete-time recurrent neural networks
Mahmoud, M. S.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING, 2009, 223 (I8) : 1045 - 1053

← 1 2 3 4 5 →