Title Multilogistic regression by means of evolutionary product-unit neural networks
Authors Hervás-Martínez C. , MARTÍNEZ ESTUDILLO, FRANCISCO JOSÉ, CARBONERO RUZ, MARIANO
External publication No
Means Neural Networks
Scope Article
Nature Científica
JCR Quartile 1
SJR Quartile 1
JCR Impact 2.656
SJR Impact 1.141
Web https://www.scopus.com/inward/record.uri?eid=2-s2.0-51049123604&doi=10.1016%2fj.neunet.2007.12.052&partnerID=40&md5=13be5672d62d920739c7285dfe029b72
Publication date 01/01/2008
ISI 000260550300008
Scopus Id 2-s2.0-51049123604
DOI 10.1016/j.neunet.2007.12.052
Abstract We propose a multilogistic regression model based on the combination of linear and product-unit models, where the product-unit nonlinear functions are constructed with the product of the inputs raised to arbitrary powers. The estimation of the coefficients of the model is carried out in two phases. First, the number of product-unit basis functions and the exponents\' vector are determined by means of an evolutionary neural network algorithm. Afterwards, a standard maximum likelihood optimization method determines the rest of the coefficients in the new space given by the initial variables and the product-unit basis functions previously estimated. We compare the performance of our approach with the logistic regression built on the initial variables and several learning classification techniques. The statistical test carried out on twelve benchmark datasets shows that the proposed model is competitive in terms of the accuracy of the classifier. © 2008 Elsevier Ltd. All rights reserved.
Keywords Artificial intelligence; Classification (of information); Computer networks; Materials handling; Maximum likelihood estimation; Statistical tests; Vegetation; Basis functions; Evolutionary neural networks; Multi-class classification; Multilogistic regression; Neural networks; article; artificial neural network; computer model; evolutionary algorithm; intermethod comparison; learning algorithm; multivariate logistic regression analysis; network learning; priority journal; statistical model; Algorithms; Animals; Evolution; Humans; Information Storage and Retrieval; Learning; Likelihood Functions; Logistic Models; Neural Networks (Computer); Nonlinear Dynamics; Signal Processing, Computer-Assisted
Universidad Loyola members

Change your preferences Manage cookies