Three neural networks for nonlinear optimization

Abstract

The online solution of optimization (including minimization and maximization) is viewed as a basic and important issue, which has been widely arisen in scientific researches and engineering applications. In this paper, a new recurrent neural network (NRNN) is generalized and investigated for the nonlinear optimization problem. In addition, two gradient neural networks are employed for comparison. Theoretical analysis of convergence is presented to demonstrate the exponential convergence of the proposed new recurrent neural network. Simulation results based on computer further demonstrate the efficacy and advantages of the proposed new recurrent neural network, compared with two gradient-based neural networks.