Function optimization by RPLNN
Mohammad Bagher Menhaj, Navid Seifipour · 2003
This paper introduces a model-free optimization method, called ring probabilistic logic neural networks (RPLNNs), for function optimization. In order to compare the performance of RPLNNs with that of conventional genetic algorithms (CGAs), two different optimization problems have been considered. The simulation results show that the RPLNN remarkably outperforms the CGA and some gradient-based methods as well.