Multistability of Switched Neural Networks With Gaussian Activation Functions Under State-Dependent Switching

This article presents theoretical results on the multistability of switched neural networks with Gaussian activation functions under state-dependent switching. It is shown herein that the number and location of the equilibrium points of the switched neural networks can be characterized by making use of the geometrical properties of Gaussian functions and local linearization based on the Brouwer fixed-point theorem. Four sets of sufficient conditions are derived to ascertain the existence of 7^p15^p23^p3; equilibrium points, and 4^p13^p22^p3 of them are locally stable, wherein p₁, p₂, and p₃ are nonnegative integers satisfying 0 ≤ p₁ + p₂ + p₃ ≤ n and n is the number of neurons. It implies that there exist up to 7ⁿ equilibria, and up to 4ⁿ of them are locally stable when p₁ = n. It also implies that properly selecting p₁, p₂, and p₃ can engender a desirable number of stable equilibria. Two numerical examples are elaborated to substantiate the theoretical results.