Convergence analysis of general neural networks under almost periodic stimuli

In this paper, we investigate the convergence dynamics of 2N almost periodic encoded patterns of general neural networks subjected to external almost periodic stimuli, including almost periodic delays. Invariant regions are established for the existence of 2N almost periodic encoded patterns under two classes of activation functions. By employing the property of ℳ︁‐cone and inequality technique, attracting basins are estimated and some criteria are derived for the networks to converge exponentially toward 2N almost periodic encoded patterns. The results obtained are new; they extend and generalize the corresponding results existing in the previous literature.