The Problem of Fragile Feature Subset Preference in Feature Selection Methods and A Proposal of Algorithmic Workaround

Somol Petr



Název
The Problem of Fragile Feature Subset Preference in Feature Selection Methods and A Proposal of Algorithmic Workaround
Autor
lupa Somol Petr UTIA-B - Ústav teorie informace a automatizace AV ČR, v. v. i.
Spoluautoři
lupa Grim Jiří UTIA-B - Ústav teorie informace a automatizace AV ČR, v. v. i.
lupa Pudil Pavel UTIA-B - Ústav teorie informace a automatizace AV ČR, v. v. i.
Zdroj.dok.
lupa Proc. 2010 Int. Conf. on Pattern Recognition. S. 4396-4399. - Istanbul : IEEE Computer Society, 2010
Vyd.údaje
4 s. : flash
Druh dok.
C
Jazyk dok.
eng
Země vyd.
TR
Klíč.slova
feature selection * machine learning * over-fitting * classification * feature weights * weighted features * feature acquisition cost
URL
http://library.utia.cas.cz/separaty/2010/RO/somol-the problem of fragile feature subset preference in feature selection methods and a proposal of algorithmic workaround.pdf
Databáze
zc - Konferenční příspěvek (zahraniční konference)
URL
http://library.utia.cas.cz/separaty/2010/RO/somol-the problem of fragile feature subset preference in feature selection methods and a proposal of algorithmic workaround.pdf http://library.utia.cas.cz/separaty/2010/RO/somol-the problem of fragile feature subset preference in feature selection methods and a proposal of algorithmic workaround.pdf
Trvalý link
http://hdl.handle.net/11104/0189152