Convergence properties of radial basis functions networks in function learning
Krzyzak A, Niemann H (2021)
Publication Type: Conference contribution
Publication year: 2021
Journal
Publisher: Elsevier B.V.
Book Volume: 192
Pages Range: 3761-3767
Conference Proceedings Title: Procedia Computer Science
Event location: Szczecin
DOI: 10.1016/j.procs.2021.09.150
Abstract
In this article we consider asymptotic properties of the normalized radial basis function networks with one hidden layer trained by independent patterns with arbitrary distributions. Convergence and rates of convergence are investigated and the choice of the radial basis functions and the network parameters are discussed.
Authors with CRIS profile
Involved external institutions
How to cite
APA:
Krzyzak, A., & Niemann, H. (2021). Convergence properties of radial basis functions networks in function learning. In Jaroslaw Watrobski, Wojciech Salabun, Carlos Toro, Cecilia Zanni-Merk, Robert J. Howlett, Lakhmi C. Jain, Lakhmi C. Jain (Eds.), Procedia Computer Science (pp. 3761-3767). Szczecin, PL: Elsevier B.V..
MLA:
Krzyzak, Adam, and Heinrich Niemann. "Convergence properties of radial basis functions networks in function learning." Proceedings of the 25th KES International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2021, Szczecin Ed. Jaroslaw Watrobski, Wojciech Salabun, Carlos Toro, Cecilia Zanni-Merk, Robert J. Howlett, Lakhmi C. Jain, Lakhmi C. Jain, Elsevier B.V., 2021. 3761-3767.
BibTeX: Download