Supervised Learning Errors by Radial Basis Function Neural Networks and Regularization Networks

Autor:	Roman Neruda, Petra Vidnerová
Rok vydání:	2008
Předmět:	Artificial neural network Radial basis function neural Computer science business.industry Supervised learning Radial basis function Artificial intelligence Special case business Regularization (mathematics) Regularization theory
Zdroj:	2008 Second International Conference on Future Generation Communication and Networking Symposia.
Popis:	There is a gap between the theoretical results of regularization theory and practical suitability of regularization-derived networks (RN). On the other hand, radial basis function networks (RBF) that can be seen as a special case of regularization networks, have a rich selection of learning algorithms. In this work we study a relationship between RN and RBF, and show that theoretical estimates for RN hold for a concrete RBF applied on real-world data.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::b9059a3933ae2433c29e83b31b8599d9 https://doi.org/10.1109/fgcns.2008.57 Zobrazit plný text záznamu