Learning with Generalization Capability by Kernel Methods of Bounded Complexity

0405215 - UIVT-O 330387 RIV NL eng J - Journal Article
Kůrková, Věra - Sanguineti, M.
Learning with Generalization Capability by Kernel Methods of Bounded Complexity.
[Učení se schopností generalizace pomocí jádrových metod omezené složitosti.]
Journal of Complexity. Roč. 21, č. 3 (2005), s. 350-367. ISSN 0885-064X. E-ISSN 1090-2708
R&D Projects: GA AV ČR 1ET100300419
Institutional research plan: CEZ:AV0Z10300504
Keywords : supervised learning * generalization * model complexity * kernel methods * minimization of regularized empirical errors * upper bounds on rates of approximate optimization
Subject RIV: BA - General Mathematics
Impact factor: 1.186, year: 2005

Learning from data with generalization capability is studied in the framework of minimization of regularized empirical error functionals over nested families of hypothesis sets with increasing model complexity.

Učení na základě dat se schopností generalizace je studováno v rámci minimalizace regularizované empirické chyby na hypotetických množinách s rostoucí modelovou složitostí.
Permanent Link: http://hdl.handle.net/11104/0125406