Inverse Problems in Learning from Data

0349057 - ÚI 2011 RIV PT eng C - Konferenční příspěvek (zahraniční konf.)
Kůrková, Věra
Inverse Problems in Learning from Data.
ICNC 2010. Proceedings of the International Conference on Neural Computation. Setúbal: SciTePress, 2010 - (Filipe, J.; Kacprzyk, J.), s. 316-321. ISBN 978-989-8425-32-4.
[ICNC 2010. International Conference on Neural Computation. Valencia (ES), 24.08.2010-26.08.2010]
Grant CEP: GA MŠMT OC10047
Výzkumný záměr: CEZ:AV0Z10300504
Klíčová slova: learning from data * minimization of empirical and expected error functionals * reproducing kernel Hilbert spaces
Kód oboru RIV: IN - Informatika

It is shown that application of methods from theory of inverse problems to learning from data leads to simple proofs of characterization of minima of empirical and expected error functionals and their regularized versions. The reformulation of learning in terms of inverse problems also enables comparison of regularized and non regularized case showing that regularization achieves stability by merely modifying output weights of global minima. Methods of theory of inverse problems lead to choice of reproducing kernel Hilbert spaces as suitable ambient function spaces.
Trvalý link: http://hdl.handle.net/11104/0189395