Enhanced maxcut clustering with multivalued neural networks and functional annealing

Combinatorial optimization
Neural networks
Authors

Enrique Mérida Casermeiro

Domingo López-Rodríguez

Juan Miguel Ortiz-de-Lazcano-Lobato

Published

1 April 2006

Publication details

ESANN 2006 Proceedings - 14th European Symposium on Artificial Neural Networks, pp. 25–30

Links

 

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.

@InProceedings{Casermeiro2006,
     author = {Enrique Mérida Casermeiro and Domingo López-Rodríguez and Juan Miguel Ortiz-de-Lazcano-Lobato},
     booktitle = {{ESANN} 2006, 14th European Symposium on Artificial Neural Networks, Bruges, Belgium, April 26-28, 2006, Proceedings},
     title = {Enhanced maxcut clustering with multivalued neural networks and functional annealing},
     year = {2006},
     pages = {25–30},
     publisher = {d-side publication},
     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. © 2006 i6doc.com publication. All rights reserved.},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     biburl = {https://dblp.org/rec/conf/esann/CasermeiroLO06.bib},
     document_type = {Conference Paper},
     journal = {ESANN 2006 Proceedings - European Symposium on Artificial Neural Networks},
     keywords = {Combinatorial optimization; Optimization, Combinatorial optimization problems; Its efficiencies; Local optima; MAX-CUT problem; Multi-valued; NP Complete; Optimization method; Recurrent models, Recurrent neural networks},
     source = {Scopus},
     timestamp = {Thu, 12 Mar 2020 11:36:02 +0100},
     url = {https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2006-86.pdf},
}