A Unified Framework for Finite-Time and Fixed-Time Stabilization of Neural Networks with General Activations and External Disturbances

Abstract

This paper develops a unified framework to study the finite-time and fixed-time stabilization (FFTS) of neural networks (NNs) with general activations and external disturbances. A new distributed control algorithm is designed to achieve the goal of FFTS for the NNs with either continuous or discontinuous activations. An upper-bound of the stabilization time is determined based on the control parameters. Numerical simulations are provided to demonstrate the robustness and disturbance rejection of the proposed control algorithm.