Testing the number of parameters with multidimensional MLP

dc.creatorRynkiewicz, Joseph
dc.date2008-02-21
dc.date.accessioned2026-07-07T09:22:31Z
dc.date.available2026-07-07T09:22:31Z
dc.descriptionThis work concerns testing the number of parameters in one hidden layer multilayer perceptron (MLP). For this purpose we assume that we have identifiable models, up to a finite group of transformations on the weights, this is for example the case when the number of hidden units is know. In this framework, we show that we get a simple asymptotic distribution, if we use the logarithm of the determinant of the empirical error covariance matrix as cost function.
dc.identifierhttps://arxiv.org/abs/0802.3141
dc.identifierhttp://arxiv.org/abs/0802.3141
dc.identifierDans ASMDA 2005 - ASMDA 2005, Brest : France (2005)
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/155402
dc.subjectStatistics Theory
dc.subjectMachine Learning
dc.titleTesting the number of parameters with multidimensional MLP
dc.typetext

Files

Collections