Almost-periodic Solutions Of Two Kinds Of Neural Network Models In The Sense Of Besicovitch

There have been a lot of studies on the existence of almost periodic solutions of some differential equations in the sense of Bohr,while the existence of almost periodic solutions in the sense of Besicovitch has hardly been studied.In this thesis,we mainly study almost periodic solution in sense of Besicovitch of two kinds of neural network models.Firstly,the definition of almost periodic function in the sense of Besicovitch and the related lemma proof are given.Then,the existence of almost periodic solutions in the sense of Beicovitch for fractional-order quaternion-valued and Clifford-valued fuzzy cellular neural networks with time-varying delays are respectively obtained by using the relevant theories and Banach fixed point theorem.Finally,Gronwall inequality techniques and a proof by contradiction are used to analyze the stability of the solutions of the two kinds of neural networks and numerical example are given to illustrate the feasibility of our results.