Enhanced maxcut clustering with multivalued neural networks and functional annealing

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

PDF

 

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

How to cite

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.

BibTeX

<pre><code>

@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}, }

<button class='copy-bib-btn' id='copy-bib-btn'><i class='bi bi-clipboard'></i> Copy BibTeX</button>