Multistability of almost periodic solutions of neural networks with discontinuous activation functions

In this paper, we investigate the multistablility of almost periodic solutions of neural networks with a class of discontinuous activation functions. It shows that the n-neuron neural networks can have (r + 1)ⁿ (r ≥ 1) exponentially stable almost periodic solutions. As special cases, the multiperiodicity and multistability of neural networks with periodic or constant coefficients are derived respectively. Furthermore, an example is presented to illustrate the effectiveness of our results.