A new upper bound for global asymptotic robust stability of BAM neural networks under multiple time-delays

This research looks at a new upper bound for bidirectional associative memory (BAM) delayed neural networks under global asymptotic robust stability (GARS) condition. For the suggested system, our new bound will provide different outcomes. In the process of determining necessary circumstances for the suggested BAM neural system's equilibrium point, an appropriate L- K functional (LKF) and activation functions were used. Our BAM model's stated necessary requirements are never reliant on time delay factors. The advantages of the proposed results over the previously discussed upper bound norm results are demonstrated numerically towards the end of this study.