Abstract
Studies on the stability of the equilibrium points of continuous bidirectional associative memory (BAM) neural network have yielded many useful results. A novel neural network model called standard neural network model (SNNM) is advanced. By using state affine transformation, the BAM neural networks were converted to SNNMs. Some sufficient conditions for the global asymptotic stability of continuous BAM neural networks were derived from studies on the SNNMs' stability. These conditions were formulated as easily verifiable linear matrix inequalities (LMIs), whose conservativeness is relatively low. The approach proposed extends the known stability results, and can also be applied to other forms of recurrent neural networks (RNNs).
This is a preview of subscription content, log in via an institution to check access.
References
Barabanov, N.E., Prokhorov, D.V., 2002. Stability analysis of discrete-time recurrent neural networks.IEEE Trans on Neural Networks,13(2): 292–303.
Boyd, S.P., Ghaoui, L.E., Feron, E., Balakrishnan, V., 1994. Linear Matrix Inequalities in System and Control Theory. SIAM, Philadelphia, PA, p. 23–24, 120.
Cao, J.D., Wang, L., 2002. Exponential stability and periodic oscillatory solution in BAM networks with delays.IEEE Trans on Neural Networks,13(2): 457–463.
Fu, Y.L., Zhao, Y., Fan, Z., Liao, X.X., 2000. Bidirectional associative memory model with delays.J Huazhong Univ of Sci & Tech,28(7): 80–82 (in Chinese).
Gahinet, P., Nemirovski, A., Laub, A.J., Chilali, M., 1995. LMI Control Toolbox. The Math Works Inc., Natick, MA.
Jing, C., 1997. Asymptotic stability of continuous bidirectional associative memory networks.Pattern Recognition and Artificial Intelligence,10(1): 81–86 (in Chinese).
Kosko, B., 1987. Adaptive bidirectional associative memories.Appl Opt,26(23): 4947–4960.
Liao, X.X., 2000. Theory and Application of Stability for Dynamical Systems. National Defence Industrial Press. Beijing, China, p. 186–214 (in Chinese).
Liu, M.Q., Zhang, S.L., 2003. Stability analysis of a class of discrete-time recurrent neural networks: an LMI approach.Journal of Zhejiang University (Engineering Science),37(1): 19–23 (in Chinese).
Moore, J.B., Anderson, B.D.O., 1968. A generalization of the Popov criterion.Journal of the Franklin Institute,285(6): 488–492.
Suykens, J.A.K., Vandewalle, J., Moor, B.D., 1998. An absolute stability criterion for the Lur'e problem with sector and slope restricted nonlinearities.IEEE Trans on Circuits and Systems-I,45(9): 1007–1009.
Xu, B.Z., Zhang, B.L., Kwong, C.P., 1992. Asymptotic Stability Analysis of Continuous Bidirectional Associative Memory Networks. IEEE International Conference on Systems Engineering, Kobe, Japan, p. 572–575.
Zhang, B.L., Xu, B.Z., Kwong, P.K., 1993. Performance analysis of the bidirectional associative memory and an improved model from the matched-filtering viewpoint.IEEE Trans on Neural Networks,4(5): 864–872.
Author information
Authors and Affiliations
Additional information
Project (No. 60074008) supported by the National Natural Science Foundation of China
Rights and permissions
About this article
Cite this article
Sen-lin, Z., Mei-qin, L. LMI-based approach for global asymptotic stability analysis of continuous BAM neural networks. J. Zheijang Univ.-Sci. A 6, 32–37 (2005). https://doi.org/10.1631/BF02842474
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/BF02842474
Key words
- Standard neural network model (SNNM)
- Bidirectional associative memory (BAM) neural network
- Linear matrix inequality (LMI)
- Linear differential inclusion (LDI)
- Global asymptotic stability