Extended dissipative performance of fractional-order neural networks via LMI approach

This paper investigates the extended dissipativity performance of a specific category of fractional-order neural networks. The derivatives involving fractional-order has been considered in the sense of Caputo’s derivative due to their significance over the other fractional derivatives. In contrast to other research, the primary goal of this paper is to provide a response to the question of whether extended dissipativity criteria can be extended to fractional-order neural networks. By offering a method for evaluating the required performance for fractional-order neural networks, this goal has been accomplished successfully. A suitable condition has been developed using the notion of linear matrix inequality to guarantee the required performance for the class of fractional-order neural networks under consideration. Lastly, the proposed theoretical results are verified through numerical examples along with simulation results.