Surrogate Modelling of Solutions of Integral Equations by Neural Networks

Authors: Věra Kůrková
Publication year: 2012
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Artificial Intelligence Applications and Innovations
Projects: Analysis of Intelligent Computational Distributed Systems
Bibliographic citation: KŮRKOVÁ, Věra. Surrogate Modelling of Solutions of Integral Equations by Neural Networks. In: ILIADIS, L.S., MAGLOGIANNIS, I., PAPADOPOULOS, H., eds. Artificial Intelligence Applications and Innovations. Heidelberg: Springer, 2012, S. 88-96. IFIP Advances in Information and Communication Technology, 381. ISBN 978-3-642-33408-5. ISSN 1868-4238
Dostupné z: doi:10.1007/978-3-642-33409-2_10
DOI: 10.1007/978-3-642-33409-2_10
ID: 379775

Abstract

Surrogate modelling of solutions of integral equations by neural networks is investigated theoretically. Estimates of speed of convergence of suboptimal surrogate solutions to solutions described by Fredholm theorem are derived.