Periodic solutions for nonautonomous discrete-time neural networks (Q2488692)

The authors are concerned with the following nonautonomous transiently chaotic neural networks (NTCNN) \[ y_i(t+1)=k(t)y_i(t)+\sum_{j=1}^{n}w_{ij}(t)x_j(t)+a_i(t)-w_{ii}(t)a_{0i}(t), \] \[ x_i(t)=\frac{1}{1+e^{-y_i(t)\diagup \varepsilon}}. \] By using Mawhin's continuation theorem, they obtain the existence of at least one periodic solution for the NTCNN model. Sufficient conditions are also obtained for the existence of an asymptotically stable periodic solution. Numerical simulations are given at the end of the paper. As a special case, the existence of a fixed point to the corresponding autonomous discrete-time neural networks is shown, which corrects the error in the paper by \textit{W. R. Zhao, W. Lin, R.S. Liu} and \textit{J. Ruan} [IEEE Trans. Circuits Syst. I, Fund. Theory Appl. 49, No. 10, 1516--1520 (2002)].