Faculty of Information Technology, BUT

Publication Details

Restricted Boltzman Machines for Image Tag Suggestion

KRÁL Jiří and HRADIŠ Michal. Restricted Boltzman Machines for Image Tag Suggestion. In: Proceedings of the 19th Conference STUDENT EEICT 2012. Brno: Brno University of Technology, 2012, p. 5.
Type
conference paper
Language
english
Authors
Král Jiří, Ing. (DITS FIT BUT)
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT)
URL
Abstract
In this paper, we propose to model dependencies among binary variables in semantic tagging and similar tasks by Restricted Boltzmann Machines (RBM). In the proposed approach, Gibbs sampling allows learning RBMs even on data with large portion of missing values. Similarly, Gibbs sampling is used to estimate marginal probabilities of tags. The results show that the tag predictions become more certain with higher portion of known tags, and that the approach could be used for tag suggestion or semi-supervised learning.
Published
2012
Pages
5
Proceedings
Proceedings of the 19th Conference STUDENT EEICT 2012
Conference
Student EEICT 2012, Brno, CZ
Publisher
Brno University of Technology
Place
Brno, CZ
BibTeX
@INPROCEEDINGS{FITPUB9976,
   author = "Ji\v{r}\'{i} Kr\'{a}l and Michal Hradi\v{s}",
   title = "Restricted Boltzman Machines for Image Tag Suggestion",
   pages = 5,
   booktitle = "Proceedings of the 19th Conference STUDENT EEICT 2012",
   year = 2012,
   location = "Brno, CZ",
   publisher = "Brno University of Technology",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9976"
}
Back to top