Global stability and Hopf bifurcation of delayed fractional-order complex-valued BAM neural network with an arbitrary number of neurons

Document Type : Research Article

Authors

1 Department of Applied Mathematics, Ferdowsi University of Mashhad, Mashhad, Iran

2 Department of Pure Mathematics, Ferdowsi University of Mashhad, Mashhad, Iran

Abstract

In this paper, a general class of fractional-order complex-valued bidirectional associative memory neural network with time delay is considered. This neural network model contains an arbitrary number of neurons, i.e. one neuron in the X-layer and other neurons in the Y-layer. Hopf bifurcation analysis of this system will be discussed. Here, the number of neurons, i.e., $n$ can be chosen arbitrarily. We study Hopf bifurcation by taking the time delay as the bifurcation parameter. The critical value of the time delay for the occurrence of Hopf bifurcation is determined. Moreover, we find two kinds of appropriate Lyapunov functions that under some sufficient conditions, global stability of the system is obtained. Finally, numerical examples are also presented.

Keywords


[1] M. Amin, K. Murase, Single-layered complex-valued neural network for real-valued classification
problems, Neurocomputing 72 (2009) 945–955.
[2] P.L. Butzer, U. Westphal, An introduction to fractional calculus, World scientific, Singapore, 2000.
[3] J. Cao, M. Xiao, Stability and Hopf bifurcation in a simplified BAM neural network with two time
delays, IEEE Trans. Neural Netw. 18 (2007) 416–430.
[4] B.S. Chen, J.J. Chen, Razumikhin-type stability theorems for functional fractional-order differential
systems and applications, Appl. Math. Comput. 254 (2015) 63–69.
[5] J. Ge, J. Xu, Synchronization and synchronized periodic solution in a simplified five-neuron BAM
neural network with delays, Neurocomputing 74 (2011) 993–999.
[6] R. Hilfer, Applications of fractional calculus in physics, World scientific, Singapore, 2001.
[7] J. Hu, J. Wang, Global stability of complex-valued recurrent neural networks with time-delays,
IEEE Trans. Neur. Netw. Learn. Syst. 23 (2012) 853–865.
[8] C. Huang, J. Cao, M. Xiao, Bifurcations in a delayed fractional complex-valued neural network,
Appl. Math. Comput. 292 (2016) 210–227.
[9] E. Javidmanesh, Global stability and bifurcation in delayed bidirectional associative memory
neural networks with an arbitrary number of neurons, J. Dyn. Syst. Meas. Control 139 (2017)
0810181–0810185.
[10] E. Javidmanesh, Z. Afsharnezhad, Bifurcation analysis of a simplified BAM neural network model
with time delays, The 43rd Annual Iranian Mathematics Conference, University of Tabriz, 27 30
August 2012, Tabriz, Iran.
[11] E. Javidmanesh, Z. Afsharnezhad, S. Effati, Existence and stability analysis of bifurcating periodic
solutions in a delayed five-neuron BAM neural network model, Nonlinear Dyn. 72 (2013) 149–164.
[12] B. Kosko, Adaptive bidirectional associative memories, Appl. Opt. 26 (1987) 4947–4960.
[13] B. Lundstorm, M. Higgs, W. Spain, A. Fairhall, Fractional differentiation by neocortical pyramidal
neurons, Nat. Neurosci. 11 (2008) 1335–1342.
[14] T. Nitta, Orthogonality of decision boundaries of complex-valued neural networks, Neur. Comput.
16 (2004) 73–97.
[15] I. Podlubny, Fractional differential equations, Academic press, NY, 1999.
[16] B. Tripathi, P. Kalra, On efficient learning machine with root-power mean neuron in complex do-
main, IEEE Trans. Neur. Netw. 22 (2011) 727–738.
[17] Z. Wang, X. Wang, Y. Li, X. Huang, Stability and Hopf Bifurcation of Fractional-Order Complex-
Valued Single Neuron Model with Time Delay, Int. J. Bifurc. Chaos 27 No. 13 (2017) 1750209–
1750209-13.
[18] F. Wang, Y. Yang, X. Xu, L. Li, Global asymptotic stability of impulsive fractional-order BAM
neural networks with time delay, Neural Comput & Appl. 28 (2017) 345–352.
[19] C. Xu, C. Aouiti, Z. Liu, A further study on bifurcation for fractional order BAM neural networks
with multiple delays, Neurocomputing 417 (2020) 501–515.
[20] C. Xu, X. He, P. Li, Global existence of periodic solutions in a six-neuron BAM neural network
model with discrete delays, Neurocomputing 74 (2011) 3257–3267.
[21] C. Xu, M. Liao, P. Li, Y. Guo, Z. Liu, Bifurcation properties for fractional order delayed BAM
neural networks, Cognit Comput. 13 (2021) 322–356.
[22] C. Xu, Z. Liu, M. Liao, P. Li, Q. Xiao, S. Yuan, Fractional-order bidirectional associate memory
(BAM) neural networks with multiple delays: The case of Hopf bifurcation, Math. Comput. Simul.
182 (2021) 471–494.
[23] C.J. Xu, X.H. Tang, M.X. Liao, Frequency domain analysis for bifurcation in a simplified tri-neuron
BAM network model with two delays, Neural Netw. 23 (2010) 872–880.
[24] Y. Yang, J. Ye, Stability and bifurcation in a simplified five-neuron BAM neural network with delays,
Chaos Solit. Fractals 42 (2009) 2357–2363.
[25] T. Zhang, H. Jiang, Z. Teng, On the distribution of the roots of a fifth degree exponential polynomial
with application to a delayed neural network model, Neurocomputing 72 (2009) 1098–1104.