Learning from Data as an Inverse Problem
Result description
We reformulate the problem of minimization of an empirical error functional as a linear inverse problem by introducing an operator defined in terms of evaluations at the input data.
Keywords
learning from datageneralizationminimization of empirical errorregularizationkernel methods
The result's identifiers
Result code in IS VaVaI
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Learning from Data as an Inverse Problem
Original language description
We reformulate the problem of minimization of an empirical error functional as a linear inverse problem by introducing an operator defined in terms of evaluations at the input data.
Czech name
Učení na základě dat jako inverzní úloha
Czech description
Problém minimalizace funkcionálu empirické chyby je přeformulován jako lineární inverzní úloha pomocí operátoru definovaného jako evaluace na vstupních datech.
Classification
Type
D - Article in proceedings
CEP classification
BA - General mathematics
OECD FORD branch
—
Result continuities
Project
GA201/02/0428: Nonlinear approximation with variable basis and neural networks
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2004
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computational Statistics
ISBN
3-7908-1554-3
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
1377-1384
Publisher name
Physica Verlag
Place of publication
Heidelberg
Event location
Prague
Event date
Aug 23, 2004
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—
Basic information
Result type
D - Article in proceedings
CEP
BA - General mathematics
Year of implementation
2004