A New Varying-Factor Finite-Time Recurrent Neural Network to Online Solving Time-Varying Sylvester Equation

This paper presents a varying-parameter finite-time recurrent neural network, called varying-factor finite-time recurrent-neural-network(VFFTNN), which is able to solve the solution of the time-varying Sylvester equation online. The proposed neural network makes the matrix coefficients vary with time and can achieve convergence in a finite time. Apart from this, the performance of the network is better than traditional networks in terms of robustness. It is theoretically proved that the proposed neural network has super exponential convergence performance. Simulation results demonstrate that this neural network has faster convergence speed and better robustness than the return to zero neural networks, and can effectively track the theoretical solution of the time-varying Sylvester equation.