Learning from Data as an Optimization and Inverse Problem

0376629 - ÚI 2013 RIV DE eng C - Konferenční příspěvek (zahraniční konf.)
Kůrková, Věra
Learning from Data as an Optimization and Inverse Problem.
Computational Intelligence. Heidelberg: Springer, 2012 - (Madani, K.; Correia, A.; Rosa, A.; Filipe, J.), s. 361-372. Studies in Computational Intelligence, 399. ISBN 978-3-642-27533-3. ISSN 1860-949X.
[IJCCI 2010. International Joint Conference on Computational Intelligence. Valencia (ES), 24.10.2010-26.10.2010]
Grant CEP: GA ČR GAP202/11/1368
Výzkumný záměr: CEZ:AV0Z10300504
Klíčová slova: learning from data * minimization of empirical error * inverse problems * reproducing kernel Hilbert spaces
Kód oboru RIV: IN - Informatika

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.
Trvalý link: http://hdl.handle.net/11104/0007313