Investigation of the determinism of complex dynamical systems using simple back propagation neural networks

Improved global robust delay-dependent stability criteria for delayed cellular neural networks

“…(13) and (14), Theorem 3.1 cannot be directly used to determine the stability of the CNN (8). The following result is given to provide a sufficient condition for guaranteeing the feasibility of Equations (13) and (14). Its proof can be easily concluded combining Equations (13), (14), and (3), and hence omitted for brevity.…”

“…[15], it follows from Equation (34) that the time-delay system (8) is asymptotically stable for all admissible parameter uncertainties, which completes the proof. (13) and (14), Theorem 3.1 cannot be directly used to determine the stability of the CNN (8). The following result is given to provide a sufficient condition for guaranteeing the feasibility of Equations (13) and (14).…”

“…The following result is given to provide a sufficient condition for guaranteeing the feasibility of Equations (13) and (14). Its proof can be easily concluded combining Equations (13), (14), and (3), and hence omitted for brevity. (λ i,1 , λ i,2 , .…”

“…Since time delays inevitably exist in the neural networks (NNs), and are frequently important sources of oscillation and instability [3,4,8,13,14,16], various efforts have been paid in the past few years for the analysis of CNNs with various time delays, (see e.g. [5,11,18,20,21,[23][24][25][26][30][31][32]36] and references therein).…”