Enhanced maxcut clustering with multivalued neural networks and functional annealing
Abstract
In this work a new algorithm to improve the performance of optimization methods, by means of avoiding certain local optima, is described. Its theoretical bases are presented in a rigorous, but intuitive, way. It has been applied 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 benchmark. Our proposal outperforms other specialized and powerful techniques, as shown by simulations.
Citation
Please, cite this work as:
[CLO06] E. M. Casermeiro, D. López-Rodríguez, and J. M. Ortiz-de-Lazcano-Lobato. “Enhanced maxcut clustering with multivalued neural networks and functional annealing”. In: ESANN 2006, 14th European Symposium on Artificial Neural Networks, Bruges, Belgium, April 26-28, 2006, Proceedings. d-side publication, 2006, pp. 25-30. URL: https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2006-86.pdf.