Multistability and associative memory of neural networks with Morita-like activation functions

This paper presents the multistability analysis and associative memory of neural networks (NNs) with Morita-like activation functions. In order to seek larger memory capacity, this paper proposes Morita-like activation functions. In a weakened condition, this paper shows that the NNs with n-neurons have (2m + 1)(n) equilibrium points (Eps) and (m + 1)(n) of them are locally exponentially stable, where the parameter m depends on the Morita-like activation functions, called Morita parameter. Also the attraction basins are estimated based on the state space partition. Moreover, this paper applies these NNs into associative memories (AMs). Compared with the previous related works, the number of Eps and AM's memory capacity are extensively increased. The simulation results are illustrated and some reliable associative memories examples are shown at the end of this paper. (C) 2021 Elsevier Ltd. All rights reserved.

Automated summary

This paper discusses the multistability analysis and associative memory of neural networks with Morita-like activation functions, proposing a larger memory capacity. The NNs with n-neurons have equilibrium points and locally exponentially stable points, with the parameter m depending on the Morita-like activation functions. The application of these NNs to associative memories results in significantly increased memory capacity compared to previous works.