Anti-periodic solutions for Cohen–Grossberg neural networks with bounded and unbounded delays

In this paper, a class of Cohen–Grossberg neural networks (CGNNs) with bounded and unbounded delays are considered. We establish some sufficient conditions on the existence and exponential stability of anti-periodic solutions for the following Cohen–Grossberg neural networks x i ′ ( t ) = - a i ( x i ( t ) ) b i ( x i ( t ) ) - ∑ j = 1 n c ij ( t ) f j ( x j ( t ) ) - ∑ j = 1 n d ij ( t ) g j ( x j ( t - τ ij ( t ) ) ) - ∑ j = 1 n e ij ( t ) ∫ 0 ∞ k ij ( θ ) h j ( x j ( t - θ ) ) d θ - I i ( t ) , i = 1 , 2 , … , n . Moreover, we also present an example to illustrate the feasibility and effectiveness of our results.