000065228 001__ 65228 000065228 005__ 20200221144339.0 000065228 0247_ $$2doi$$a10.1016/j.neucom.2015.07.069 000065228 0248_ $$2sideral$$a92294 000065228 037__ $$aART-2016-92294 000065228 041__ $$aeng 000065228 100__ $$0(orcid)0000-0001-8749-8291$$aLacruz, B.$$uUniversidad de Zaragoza 000065228 245__ $$aµG2-ELM: an upgraded implementation of µ G-ELM 000065228 260__ $$c2016 000065228 5060_ $$aAccess copy available to the general public$$fUnrestricted 000065228 5203_ $$aµG-ELM is a multiobjective evolutionary algorithm which looks for the best (in terms of the MSE) and most compact artificial neural network using the ELM methodology. In this work we present the µG2-ELM, an upgraded version of µG-ELM, previously presented by the authors. The upgrading is based on three key elements: a specifically designed approach for the initialization of the weights of the initial artificial neural networks, the introduction of a re-sowing process when selecting the population to be evolved and a change of the process used to modify the weights of the artificial neural networks. To test our proposal we consider several state-of-the-art Extreme Learning Machine (ELM) algorithms and we confront them using a wide and well-known set of continuous, regression and classification problems. From the conducted experiments it is proved that the µG2-ELM shows a better general performance than the previous version and also than other competitors. Therefore, we can guess that the combination of evolutionary algorithms with the ELM methodology is a promising subject of study since both together allow for the design of better training algorithms for artificial neural networks. 000065228 536__ $$9info:eu-repo/grantAgreement/ES/DGA/E22$$9info:eu-repo/grantAgreement/ES/DGA/E58 000065228 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/ 000065228 590__ $$a3.317$$b2016 000065228 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b24 / 133 = 0.18$$c2016$$dQ1$$eT1 000065228 592__ $$a0.879$$b2016 000065228 593__ $$aArtificial Intelligence$$c2016$$dQ1 000065228 593__ $$aComputer Science Applications$$c2016$$dQ1 000065228 593__ $$aCognitive Neuroscience$$c2016$$dQ2 000065228 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion 000065228 700__ $$0(orcid)0000-0003-1320-0223$$aLahoz, D.$$uUniversidad de Zaragoza 000065228 700__ $$0(orcid)0000-0003-2988-7728$$aMateo, P. M.$$uUniversidad de Zaragoza 000065228 7102_ $$12007$$2265$$aUniversidad de Zaragoza$$bDpto. Métodos Estadísticos$$cÁrea Estadís. Investig. Opera. 000065228 773__ $$g171 (2016), 1302-1312$$pNeurocomputing$$tNEUROCOMPUTING$$x0925-2312 000065228 8564_ $$s742040$$uhttps://zaguan.unizar.es/record/65228/files/texto_completo.pdf$$yPostprint 000065228 8564_ $$s124260$$uhttps://zaguan.unizar.es/record/65228/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint 000065228 909CO $$ooai:zaguan.unizar.es:65228$$particulos$$pdriver 000065228 951__ $$a2020-02-21-13:49:03 000065228 980__ $$aARTICLE