Enhanced MaxCut Clustering with Multivalued Neural Networks and Functional Annealing
Enrique Mérida-Casermeiro, Domingo López-Rodríguez, Juan Miguel Ortiz-de-Lazcano-Lobato · The European Symposium on Artificial Neural Networks · 2006
In this work a new algorithm to improve the performance of opti- mization methods, by means of avoiding certain local optima, is described. Its theoretical bases are presented in a rigorous, but intuitive, way. It has been ap- plied concretely to the case of recurrent neural networks, in particular to MREM, a multivalued recurrent model, that has proved to obtain very good results when dealing with NP-complete combinatorial optimization problems. In order to show its efficiency, the well-known MaxCut problem for graphs has been selected as ben- chmark. Our proposal outperforms other specialized and powerful techniques, as shown by simulations.