Existence and global exponential convergence of almost periodic solution for competitive neural networks with varying time-delays and different time-scales;

In the paper, by using the fixed point theory and differential inequality technique we study the existence and global exponential convergence of almost periodic solutions for cellular neural networks with variable delay.

In this paper the local convergence properties of the filter trust region algorithm is discussed.

The algorithm generates detectors with an r-contiguous-bits unchanged rule(r-CBUR)and a p-receptor editing to search in a wide feature space and try to avoid local convergences.

The local convergence properties of the filter trust region algorithm was discussed.

Moreover, the control laws using smooth time varying feedback do not stabilize the system at exponential convergence rate.

Existence and exponential convergence of periodic oscillatory solution for BAM neural networks with delays is discussed by using fixed-point theorem,constructing suitable Lyapunov functions,and some analysis techniques.

The feed-forward controller makes the practical robot trace in nominal system converge to the desired one with an exponential convergence rate,while the feedback controller makes the error be bounded in terminal.