On Tractability of Neural-Network Approximation

Authors: P.C. Kainen, Věra Kůrková, M. Sanguineti
Publication year: 2009
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Adaptive and Natural Computing Algorithms
Projects: Methods for Intelligent Systems and Their Applications in Datamining and Natural Language Processing
Bibliographic citation: KAINEN, P.C., KŮRKOVÁ, Věra, SANGUINETI, M. On Tractability of Neural-Network Approximation. In: KOLEHMAINEN, M., TOIVANEN, P., BELICZYNSKI, B., eds. Adaptive and Natural Computing Algorithms. Berlin: Springer, 2009, S. 11-21. Lecture Notes in Computer Science, 5495. ISBN 978-3-642-04920-0
Dostupné z: doi:10.1007/978-3-642-04921-7_2
DOI: 10.1007/978-3-642-04921-7_2
ID: 326645

Abstract

The tractability of neural-network approximation is investigated. The dependence of worst-case errors on the number of variables is studied. Estimates for Gaussian radial-basis-function and perceptron networks are derived.