Cohen-Grossberg neural networks with unpredictable and Poisson stable dynamics

In this paper, Cohen-Grossberg neural networks with unpredictable and compartmental periodic unpredictable strengths of connectivity between cells and inputs are investigated. To approve Poisson stability and unpredictability in neural networks, the method of included intervals and contraction mapping principle are used. The existence, uniqueness, and exponential stability of unpredictable and Poisson stable outputs are discussed. Examples with numerical simulations that support the theoretical results are provided. The dependence of the neural network dynamics on the numerical characteristic, the degree of periodicity, is shown.