Detail publikace

Restricted Boltzman Machines for Image Tag Suggestion

KRÁL, J.; HRADIŠ, M. Restricted Boltzman Machines for Image Tag Suggestion. Proceedings of the 19th Conference STUDENT EEICT 2012. Brno: Brno University of Technology, 2012. p. 1-5.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Král Jiří, Ing.
Hradiš Michal, Ing., Ph.D. (UPGM)
URL
Abstrakt

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.

Rok
2012
Strany
1–5
Sborník
Proceedings of the 19th Conference STUDENT EEICT 2012
Konference
Student EEICT 2012, Brno, CZ
Vydavatel
Brno University of Technology
Místo
Brno
BibTeX 
@inproceedings{BUT192815,
  author="Jiří {Král} and Michal {Hradiš}",
  title="Restricted Boltzman Machines for Image Tag Suggestion",
  booktitle="Proceedings of the 19th Conference STUDENT EEICT 2012",
  year="2012",
  pages="1--5",
  publisher="Brno University of Technology",
  address="Brno",
  url="http://www.feec.vutbr.cz/EEICT/2012/sbornik/03doktorskeprojekty/09grafikaamultimedia/03-ikral.pdf"
}
Nahoru