Global Dynamics of Delayed Bidirectional Associative Memory (BAM) Neural Networks
-
摘要: 在没有假定关联函数的光滑性,单调性和有界性的条件下,应用Liapunov泛函方法和矩阵代数技术,得到具有常数传输时滞的双向联想记忆(BAM)的神经网络模型平衡点存在性和全局指数稳定性的一些新的充分条件,这些条件可以由网络参数,连接矩阵和关联函数的Lipschitz常数所表示的M矩阵来刻化.这些结果不仅是简单和实用的,而且相对于已有文献的结果具有较少的限制和更易于验证.
-
关键词:
- 双向联想记忆(BAM) /
- 神经网络 /
- 全局指数稳定 /
- Liapunov泛函
Abstract: Without assuming the smoothness, monotonicity and boundedness of the activation functions, some novel criteria on the existence and global exponential stability of equilibrium point for delayed bidirectional associative memory (BAM) neural networks are established by applying the Liapunov functional methods and matrix-algebraic techniques. It is shown that the new conditions presented in terms of a nonsingular M matrix described by the networks parameters, the connection matrix and the Lipschitz constant of the activation functions, are not only simple and practical, but also easier to check and less conservative than those imposed by similar results in recent literature. -
[1] Mohamad S.Global exponential stability in continuous-time and discrete-time delayed bidirectional neural networks[J]Physica D,2001,159(3):233—251. [2] Liao X F,Yu J B,Chen G.Novel stability criteria for bidirectional associative memory neural networks with time delays [J].International Journal of Circuit Theory and Applications,2002,30(3):519—546. doi: 10.1002/cta.206 [3] Kosko B. Bidirectional associative memories[J]. IEEE Transactions on Systems,Man,and Cybernetics,1988,18(1):49—60. doi: 10.1109/21.87054 [4] Kosko B. Unsupervised learning in noise[J].IEEE Transactions on Neural Networks,1990,1(1):44—57. doi: 10.1109/72.80204 [5] Kosko B. Structural stability of unsupervised learning in feedback neural networks[J].IEEE Transactions on Automatic Control,1991,36(5):785—790. doi: 10.1109/9.85058 [6] Maundy B,Masry E. A switched capacitor bidirectional associative memory[J].IEEE Transactions on Circuits and Systems,1990,37(12):1568—1572. doi: 10.1109/31.101281 [7] Gopalsamy K,He X Z. Delay-independent stability in bidirectional associative memory networks[J].IEEE Transactions on Neural Networks,1994,5(7):998—1002. doi: 10.1109/72.329700 [8] Liao X F,Wong K W,Yu J B. Novel stability conditions for cellular neural networks with time delay[J].International Journal of Bifurcation and Chaos,2001,11(12):1835—1864. doi: 10.1142/S0218127401003097 [9] Morita M. Associative memory with non-monotone dynamics [J].Neural Networks,1993,6(1):115—126. doi: 10.1016/S0893-6080(05)80076-0 [10] Yoshizawa S,Morita M,Amari S. Capacity of associative memory using a non-monotonic neuron networks[J].Neural Networks,1993,6(2):167—176. doi: 10.1016/0893-6080(93)90014-N [11] Kennedy M P,Chua L O. Neural networks for nonlinear programming[J].IEEE Transactions on Circuits and Systems,1988,35(4):554—562. doi: 10.1109/31.1783 [12] ZHOU Jin,LIU Zeng-rong,CHEN Guan-rong. Dynamics of delayed periodic neural networks[J].Neural Networks,2004,16(1):87—101. [13] ZHOU Jin,CHEN Tian-ping,XIANG Lan. Robust synchronization of coupled delayed recurrent neural networks,Advances in Neural Networks-ISNN[A].Lecture Notes in Computer Science[C].Berlin Heidelberg,New York:Springer-Verlag,2004,3173(1):144—149. [14] CHEN Guan-rong,ZHOU Jin,LIU Zeng-rong. Global synchronization of coupled delayed neural networks and applications to chaotic CNN models [J].International Journal of Bifurcation and Chaos,2004,14(7):2229—2240. doi: 10.1142/S0218127404010655 [15] 向兰,周进,刘曾荣,等.具有周期输入Hopfield型神经网络的全局渐近性质[J].应用数学和力学,2002,23(12):1220—1226. [16] Hale J K.Introduction to Functional Differential Equations [M].2nd Edition.New York:Berlin Heidelberg:Springer-Verlag,1977.
点击查看大图
计量
- 文章访问数: 2577
- HTML全文浏览量: 109
- PDF下载量: 945
- 被引次数: 0