Quasi-periodic invariant 2-tori in a delayed BAM neural network

Abstract In this paper, we consider a four-neuron bi-directional associative memory (BAM, for short) neural network with two delays. We choose connection weights and the sum of delays as bifurcation parameters and derive the critical values where a double Hopf bifurcation may occur by analyzing the associated characteristic equation which is a fourth-degree polynomial exponential equation. Meanwhile, we obtain some parameter conditions on the existence of invariant 2-tori of the truncated normal form near the bifurcation point by the center manifold theorem and normal form method. Despite the fact that the higher-degree terms may destroy the invariant 2-tori of the truncated normal form, we prove that the neural network model has quasi-periodic invariant 2-tori for most of the parameter set where the truncated normal form possesses invariant 2-tori in a sufficiently small neighborhood of the bifurcation point. Numerical examples and simulations are given to support the theoretical analysis.

[1]  Wei Xing Zheng,et al.  Hopf Bifurcation of an $(n+1)$ -Neuron Bidirectional Associative Memory Neural Network Model With Delays , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Y. Kuznetsov.  Elements of Applied Bifurcation Theory , 2023, Applied Mathematical Sciences.

[3]  R. Westervelt,et al.  Stability of analog neural networks with delay. , 1989, Physical review. A, General physics.

[4]  Jinde Cao,et al.  Stability and Hopf Bifurcation in a Simplified BAM Neural Network With Two Time Delays , 2007, IEEE Transactions on Neural Networks.

[5]  Jinde Cao,et al.  Stability and Hopf bifurcation analysis on a four-neuron BAM neural network with time delays , 2006 .

[6]  L. Magalhães,et al.  Normal Forms for Retarded Functional Differential Equations and Applications to Bogdanov-Takens Singularity , 1995 .

[7]  Xiaofeng Liao,et al.  Bogdanov–Takens bifurcation in a tri-neuron BAM neural network model with multiple delays , 2013 .

[8]  Xingfu Zou,et al.  Hopf bifurcation in bidirectional associative memory neural networks with delays: analysis and computation , 2004 .

[9]  Jian Xu,et al.  Weak resonant Double Hopf bifurcations in an Inertial Four-Neuron Model with Time Delay , 2012, Int. J. Neural Syst..

[10]  Jian Xu,et al.  Computation of Synchronized Periodic Solution in a BAM Network With Two Delays , 2010, IEEE Transactions on Neural Networks.

[11]  Zhidong Teng,et al.  On the distribution of the roots of a fifth degree exponential polynomial with application to a delayed neural network model , 2009, Neurocomputing.

[12]  Xiang-Ping Yan,et al.  Bifurcation analysis in a simplified tri-neuron BAM network model with multiple delays ☆ , 2008 .

[13]  L. Magalhães,et al.  Normal Forms for Retarded Functional Differential Equations with Parameters and Applications to Hopf Bifurcation , 1995 .

[14]  Xia Liu.  Zero singularity of codimension two or three in a four-neuron BAM neural network model with multiple delays , 2014 .

[15]  Junjie Wei,et al.  Stability and Hopf bifurcation analysis on a simplified BAM neural network with delays , 2005 .

[16]  Xuemei Li.  On the persistence of quasi-periodic invariant tori for double Hopf bifurcation of vector fields , 2016 .

[17]  Sohrab Effati,et al.  Existence and stability analysis of bifurcating periodic solutions in a delayed five-neuron BAM neural network model , 2013 .

[18]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[19]  Zaijiu Shang,et al.  On the existence of invariant tori in non-conservative dynamical systems with degeneracy and finite differentiability , 2019, Discrete & Continuous Dynamical Systems - A.