CONVERGENCE ANALYSIS OF A DISCRETE-TIME RECURRENT NEURAL-NETWORK TO PERFORM QUADRATIC REAL OPTIMIZATION WITH BOUND CONSTRAINTS

This paper presents a model of a discrete-time recurrent neural networ k designed to perform quadratic real optimization with bound constrain ts, The network iteratively improves the estimate of the solution, alw ays maintaining it inside of the feasible region. Several neuron updat ing rules which assure global convergence of the net to the desired mi nimum have been obtained, Some of them also assure exponential converg ence and maximize a lower bound for the convergence degree. Simulation results are presented to show the net performance.