Multiple O(t-α) Stability of Fractional-order Switched Neural Networks with Time-varying Delays

Abstract

This article investigates multiple O(t-α) stability of fractional-order switched neural networks(FOSNNs) with time-varying delays. Under the framework of Filippov solution and geometric properties of activation function, some new results are established to ascertain the existence of equilibria. Besides, FOSNNs have more stable equilibria, which reveals that the effect of switching threshold in fractional-order neural networks. One example is provided to illustrate the effectiveness of the theoretical results.