On Periodic Solutions of a Two-Neuron Network System with Sigmoidal Activation Functions

In this paper we study the existence, uniqueness and stability of periodic solutions for a two-neuron network system with or without external inputs. The system consists of two identical neurons, each possessing nonlinear feedback and connected to the other neuron via a nonlinear sigmoidal activation function. In the absence of external inputs but with appropriate conditions on the feedback and connection strengths, we prove the existence, uniqueness and stability of periodic solutions by using the Poincare–Bendixson theorem together with Dulac's criterion. On the other hand, for the system with periodic external inputs, combining the techniques of the Liapunov function with the contraction mapping theorem, we propose some sufficient conditions for establishing the existence, uniqueness and exponential stability of the periodic solutions. Some numerical results are also provided to demonstrate the theoretical analysis.

[1]  Kiyotoshi Matsuoka,et al.  Stability conditions for nonlinear continuous neural networks with asymmetric connection weights , 1992, Neural Networks.

[2]  Charles M. Marcus,et al.  Nonlinear dynamics and stability of analog neural networks , 1991 .

[3]  Sue Ann Campbell,et al.  Stability, Bifurcation, and Multistability in a System of Two Coupled Neurons with Multiple Time Delays , 2000, SIAM J. Appl. Math..

[4]  Wang,et al.  Global stability and local stability of Hopfield neural networks with delays. , 1994, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[5]  Wen-Wei Lin,et al.  Bifurcations and Chaos in Two-Cell Cellular Neural Networks with Periodic Inputs , 2004, Int. J. Bifurc. Chaos.

[6]  Xin Wang,et al.  Discrete-Time versus Continuous-Time Models of Neural Networks , 1992, J. Comput. Syst. Sci..

[7]  F. Zou,et al.  Stability of cellular neural networks with opposite-sign templates , 1991 .

[8]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[9]  Jacques Bélair,et al.  Bifurcations, stability, and monotonicity properties of a delayed neural network model , 1997 .

[10]  Chih-Wen Shih,et al.  Complete stability for a Class of Cellular Neural Networks , 2001, Int. J. Bifurc. Chaos.

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

[12]  K. Gopalsamy,et al.  Delay induced periodicity in a neural netlet of excitation and inhibition , 1996 .

[13]  Tingshu Hu,et al.  A complete stability analysis of planar linear systems under saturation , 2000 .

[14]  Marco Gilli,et al.  On the dynamic behaviour of two-cell cellular neural networks , 1993, Int. J. Circuit Theory Appl..

[15]  Chih-Wen Shih,et al.  Complete Stability for Standard Cellular Neural Networks , 1999 .

[16]  Leon O. Chua,et al.  Cellular neural networks: applications , 1988 .

[17]  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.

[18]  Sue Ann Campbell,et al.  Frustration, Stability, and Delay-Induced Oscillations in a Neural Network Model , 1996, SIAM J. Appl. Math..

[19]  Jinde Cao,et al.  On the Exponential Stability and Periodic Solutions of Delayed Cellular Neural Networks , 2000 .