## Dynamic analysis of stochastic bidirectional associative memory neural networks with delays.(English)Zbl 1149.34054

The authors consider the stochastic bidirectional associative memory neural network model with delays $\begin{cases} du_i(t)=[-c_iu_i(t)+\sum_{j=1}^np_{ji}f_j(v_j(t-\tau_j))+I_i]\,dt +\sum_{j=1}^n\sigma_{ji}(v_j(t))\,d\omega_j(t),\\ dv_j(t)=[-d_jv_j(t)+\sum_{i=1}^nq_{ij}g_j(u_i(t-\eta_i))+J_j]\,dt +\sum_{i=1}^n\sigma_{ij}(u_i(t))\,d\omega_i(t),\quad t\geq0,\\u_i(t)=\xi(t)t,\quad v_j(t)=\zeta_j(t),\quad -\tau\leq t\leq0,\end{cases}$ with $$n$$-dimensional driving Brownian motion $$\omega=(\omega_1,\ldots,\omega_n)$$. Sufficient conditions are obtained for a.s. exponential stability, $$p$$th order exponential stability, and mean-value exponential stability. Stochastic analysis, Lyapunov functionals, and inequality technique are used.

### MSC:

 34K50 Stochastic functional-differential equations 34K20 Stability theory of functional-differential equations 60H10 Stochastic ordinary differential equations (aspects of stochastic analysis) 92C40 Biochemistry, molecular biology 92D10 Genetics and epigenetics

### Keywords:

neural network; Lyapunov functional; exponential stability
Full Text:

### References:

 [1] Kosko, B., Adaptive bi-directional associative memories, Appl opt, 26, 4947-4960, (1987) [2] Kosko, B., Bidirectional associative memories, IEEE trans syst man cybernet, 18, 49-60, (1988) [3] Kosko, B., Neural networks and fuzzy system—a dynamical system approach to machine intelligence, (1992), Prentice-Hall Englewood Cliffs (NJ), p. 38-108 [4] Huang, X.; Cao, J.; Huang, D., LMI-based approach for delay-dependent exponential stability analysis of BAM neural networks, exponential stability of delayed bi-directional associative memory networks, Chaos, solitons & fractals, 24, 885-898, (2005) · Zbl 1071.82538 [5] Song, Q.; Cao, J., Global exponential stability and existence of periodic solutions in BAM networks with delays and reaction-diffusion terms, Chaos, solitons & fractals, 23, 421-430, (2005) · Zbl 1068.94534 [6] Li, Y., Global exponential, Chaos, solitons & fractals, 24, 279-285, (2005) · Zbl 1099.68085 [7] Li, C.; Liao, X., Delay-dependent exponential stability analysis of bi-directional associative memory neural networks with time delays: an LMI approach, Chaos, solitons & fractals, 24, 1119-1134, (2005) · Zbl 1101.68771 [8] Zhang, J.; Yang, Y., Global stability analysis of bi-directional associative memory neural networks with time delays, Int J circuit theory appl, 29, 185-196, (2001) · Zbl 1001.34066 [9] Chen, A.; Huang, L.; Cao, J., Existence and stability of almost periodic solution for BAM neural networks with delays, Appl math comput, 1317, 177-193, (2003) · Zbl 1034.34087 [10] Cao, J., Global asymptotic stability of delayed bi-directional associative memory neural networks, Appl math comput, 142, 333-339, (2003) · Zbl 1031.34074 [11] Zhao, H., Global stability of bidirectional associative memory neural networks with distribute delays, Phys lett A, 297, 182-190, (2002) · Zbl 0995.92002 [12] Haykin, S., Neural networks, (1994), Prentice-Hall NJ · Zbl 0828.68103 [13] Sun, J.; Wang, L., Convergence dynamics of stochastic reaction-diffusion recurrent neural networks with delays, Int J bifurcat chaos, 15, 2131-2144, (2005) · Zbl 1092.35530 [14] Liao, X.; Mao, X., Exponential stability and instability of stochastic neural networks, Stochast anal appl, 14, 165-185, (1996) · Zbl 0848.60058 [15] Liao, X.; Mao, X., Stability of stochastic neural networks, Neural, parallel sci comput, 4, 205-224, (1996) · Zbl 1060.92502 [16] Blythe, S.; Mao, X.; Liao, X., Stability of stochastic neural networks, J franklin inst, 338, 481-495, (2001) · Zbl 0991.93120 [17] Mohammed, S., Stochastic functional differential equations, (1996), Longaman New York [18] Zhao, H.; Cao, J., New conditions for global exponential stability of cellular neural networks with delays, Neural networks, 18, 1332-1340, (2005) · Zbl 1083.68108 [19] Mitrinovic, D.; Vasic, P., Analytic inequality, (1970), Springer-Verlag New York
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.