Learning from Data as an Optimization and Inverse Problem

Authors: Věra Kůrková
Publication year: 2012
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Computational Intelligence
Projects: Learning of functional relationships from high-dimensional data
Bibliographic citation: KŮRKOVÁ, Věra. Learning from Data as an Optimization and Inverse Problem. In: MADANI, K., CORREIA, A.D., ROSA, A., FILIPE, J., eds. Computational Intelligence. Heidelberg: Springer, 2012, S. 361-372. Studies in Computational Intelligence, 399. ISBN 978-3-642-27533-3. ISSN 1860-949X
Dostupné z: doi:10.1007/978-3-642-27534-0_24
DOI: 10.1007/978-3-642-27534-0_24
ID: 376629

Abstract

Learning form data is investigated as minimization of empirical error functional in spaces of continuous functions and spaces defined by kernels. Using methods from theory of inverse problems, an alternative proof of Representer Theorem is given. Regularized and non regularized minimization of empirical error is compared.