0642799 20260226074243.420251209235959.9 85190739311 001202833900001 10.14736/kyb-2024-1-0038 22 s. P cav_un_epca*02971630023-5954601 (2024)38-59Ústav teorie informace a automatizace AV ČR, v. v. i. effective regularization quantile regression regression neural networks robust training robustness cav_un_auth*0345793 Kalina Jan UTIA-B Stochastická informatika Department of Stochastic Informatics SI SI Department of Stochastic Informatics Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0416837 Vidnerová P. CZ cav_un_auth*0435779 Janáček P. CZ https://library.utia.cas.cz/separaty/2025/SI/kalina-0642799.pdf https://www.kybernetika.cz/content/2024/1/38 GA24-10078S GA ČR CZ cav_un_auth*0472835 GA22-02067S GA ČR CZ cav_un_auth*0435776 Radial basis function (RBF) networks represent established tools for nonlinear regression modeling with numerous applications in various fields. Because their standard training is vulnerable with respect to the presence of outliers in the data, several robust methods for RBF network training have been proposed recently. This paper is interested in robust regularized RBF networks. A robust inter-quantile version of RBF networks based on trimmed least squares is proposed here. Then, a systematic comparison of robust regularized RBF networks follows, which is evaluated over a set of 405 networks trained using various combinations of robustness and regularization types. The experiments proceed with a particular focus on the effect of variable selection, which is performed by means of a backward procedure, on the optimal number of RBF units. The regularized inter-quantile RBF networks based on trimmed least squares turn out to outperform the competing approaches in the experiments if a highly robust prediction error measure is considered. WOS IN 10000 10200 10201 2026 RVO:67985556 https://hdl.handle.net/11104/0372659 S A COMPUTERSCIENCE.CYBERNETICS 1.1 0.1 14.7 0.00058 0.288 978 43 0.378 34 2.47 255 Q3 2.000 43 Q3 42.2 0.27 Q3 42.2 2024 85190739311 SCOPUS PUBMED 001202833900001 WOS cav_un_epca*0297163 Kybernetika Roč. 60 č. 1 2024 38 59 0023-5954 Ústav teorie informace a automatizace AV ČR, v. v. i.