A spectral radius-based global exponential stability for Clifford-valued recurrent neural networks involving time-varying delays and distributed delays

This paper deals with the global exponential stability for a class of Clifford-valued recurrent neural networks with time-varying delays and distributed delays (mixed time delays). The Clifford-valued neural network, as an extension of the real-valued neural network, which includes the familiar complex-valued and the quaternion-valued neural network as special cases, has been an active area of research recently. First, based on the Brouwer's fixed point theorem, the existence of the equilibrium point of Clifford-valued recurrent neural networks is established. Next, by inequality technique and the method of the Clifford-valued variation parameter, some novel assertions are given to ensure the global exponential stability of the addressed model, which are new and complement some previous works. We illustrate the effectiveness of this approach with a numerical example.

Automated summary

This paper investigates the global exponential stability of a class of Clifford-valued recurrent neural networks with time-varying delays and distributed delays. The existence of equilibrium point for Clifford-valued recurrent neural networks is established based on Brouwer's fixed point theorem. By using inequality technique and the method of the Clifford-valued variation parameter, novel assertions are given to ensure the global exponential stability of the model, which complement some previous works. The effectiveness of this approach is illustrated with a numerical example.