Abstract
A general class of discrete-time recurrent neural networks (DTRNNs) is formulated and studied in this paper. Several sufficient conditions are obtained to ensure the global stability of DTRNNs with delays based on induction principle (not based on the well-known Liapunov methods). The obtained results have neither assumed the symmetry of the connection matrix, nor boundedness, monotonicity or the differentiability of the activation functions. In addition, discrete-time analogues of a general class of continuous-time recurrent neural networks (CTRNNs) are derived and studied. The convergence characteristics of CTRNNs are preserved by the discrete-time analogues without any restriction imposed on the uniform discretization step size. Finally, the simulating results demonstrate the validity and feasibility of our proposed approach.
Similar content being viewed by others
Reference
J.J. Hopfield (1984) ArticleTitleNeurons with graded response have collective computational properties like those of two-state neurons Proceeding National Academy Science 81 3088–3092
L.O. Chua L. Yang (1988) ArticleTitleCellular neural networks: Theory IEEE Transactions Circuits Systems 35 IssueID10 1257–1272 Occurrence Handle10.1109/31.7600
L.O. Chua L. Yang (1988) ArticleTitleCellular neural networks: Applications IEEE Transactions Circuits Systems 35 IssueID10 1273–1290 Occurrence Handle10.1109/31.7601
M. Forti A. Tesi (1995) ArticleTitleNew conditions for global stability of neural networks with application to linear and quadratic programming problems IEEE Transactions Circuits Systems I 42 354–366 Occurrence Handle10.1109/81.401145
X.X. Liao J. Wang (2003) ArticleTitleAlgebraic criteria for global exponential stability of cellular neural networks with multiple time delays IEEE Transactions Circuits and Systems I 50 268–275 Occurrence Handle10.1109/TCSI.2002.808213
C. Sun C. Feng (2003) ArticleTitleGlobal robust exponential stability of interval neural networks with delays Neural Processing Letters 17 107–115 Occurrence Handle10.1023/A:1022999219879
G. Grassi (2001) ArticleTitleOn discrete-time cellular neural networks for associative memories IEEE Transactions Circuits Systems I 48 107–111 Occurrence Handle10.1109/81.903193
D. Liu A.N. Michel (1994) ArticleTitleSparsely interconnected neural networks for associative memories with applications to cellular neural networks IEEE Transactions Circuits Systems II 41 295–307 Occurrence Handle10.1109/82.285706
A.N. Michel K. Wang D. Liu H. Ye (1995) ArticleTitleQualitative limitations incurred in implementations of recurrent neural networks IEEE Transactions Control Systems Technology 15 52–65 Occurrence Handle10.1109/37.387618
M. Brucoli L. Carnimeo G. Grassi (1995) ArticleTitleDiscrete-time cellular neural networks for associative memories with learning and forgetting capabilities IEEE Transactions Circuits Systems I 42 396–399 Occurrence Handle10.1109/81.401156
R. Perfetti (1999) ArticleTitleDual-mode space-varying self-designing cellular neural networks for associative memory IEEE Transactions Circuits Systems I 46 1281–1285 Occurrence Handle10.1109/81.795841
T. Roska L.O. Chua (1992) ArticleTitleCellular neural networks with nonlinear and delay-type template International Journal Circuit Theory Appl. 20 469–481
N.E. Barabanov D.V. Prokhorov (2002) ArticleTitleStability Analysis of Discrete-Time Recurrent Neural Networks IEEE Transactions Neural Networks 13 292–303 Occurrence Handle10.1109/72.991416
S. Mohamad K. Gopalsamy (2003) ArticleTitleExponential stability of continuous-time and discrete-time cellular neural networks with delays Applied Mathematics and Computation 135 17–38 Occurrence Handle10.1016/S0096-3003(01)00299-5
Z. Zeng J. Wang X.X. Liao (2003) ArticleTitleGlobal exponential stability of a general class of recurrent neural networks with time-varying delays IEEE Transactions Circuits and Systems Part I 50 IssueID10 1353–1358 Occurrence Handle10.1109/TCSI.2003.817760
E. Liz J.B. Ferreiro (2002) ArticleTitleA note on the global stability of generalized difference equations Applied Mathematics Letters 15 655–659 Occurrence Handle10.1016/S0893-9659(02)00024-1
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zeng, Z., Huang, DS. & Wang, Z. Global Stability of a General Class of Discrete-Time Recurrent Neural Networks. Neural Process Lett 22, 33–47 (2005). https://doi.org/10.1007/s11063-004-8194-4
Issue Date:
DOI: https://doi.org/10.1007/s11063-004-8194-4