DC Field | Value | Language |
---|---|---|
dc.contributor.author | Song, Hyun Ah | ko |
dc.contributor.author | Lee, Soo-Young | ko |
dc.date.accessioned | 2023-10-24T07:00:39Z | - |
dc.date.available | 2023-10-24T07:00:39Z | - |
dc.date.created | 2023-10-24 | - |
dc.date.issued | 2013-05 | - |
dc.identifier.citation | 1st International Conference on Learning Representations, ICLR 2013 | - |
dc.identifier.uri | http://hdl.handle.net/10203/313716 | - |
dc.description.abstract | In 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.language | English | - |
dc.publisher | International Conference on Learning Representations, ICLR | - |
dc.title | Hierarchical data representation model - Multi-layer NMF | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85083953747 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 1st International Conference on Learning Representations, ICLR 2013 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Scottsdale | - |
dc.contributor.localauthor | Lee, Soo-Young | - |
dc.contributor.nonIdAuthor | Song, Hyun Ah | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.