DSpace at KOASAS
College of Engineering(공과대학)School of Electrical Engineering(전기및전자공학부)EE-Conference Papers(학술회의논문)

Hierarchical data representation model - Multi-layer NMF

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 47
  • Download : 0
Export
DC FieldValueLanguage
dc.contributor.authorSong, Hyun Ahko
dc.contributor.authorLee, Soo-Youngko
dc.date.accessioned2023-10-24T07:00:39Z-
dc.date.available2023-10-24T07:00:39Z-
dc.date.created2023-10-24-
dc.date.issued2013-05-
dc.identifier.citation1st International Conference on Learning Representations, ICLR 2013-
dc.identifier.urihttp://hdl.handle.net/10203/313716-
dc.description.abstractIn this paper, we propose a data representation model that demonstrates hierarchical feature learning using nsNMF. We extend unit algorithm into several layers. Experiments with document and image data successfully discovered feature hierarchies. We also prove that proposed method results in much better classification and reconstruction performance, especially for small number of features.-
dc.languageEnglish-
dc.publisherInternational Conference on Learning Representations, ICLR-
dc.titleHierarchical data representation model - Multi-layer NMF-
dc.typeConference-
dc.identifier.scopusid2-s2.0-85083953747-
dc.type.rimsCONF-
dc.citation.publicationname1st International Conference on Learning Representations, ICLR 2013-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationScottsdale-
dc.contributor.localauthorLee, Soo-Young-
dc.contributor.nonIdAuthorSong, Hyun Ah-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

Display Simple Item Record

qr_code

  • mendeley

    citeulike

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


rss_1.0 rss_2.0 atom_1.0