Detail publikace

Semi-supervised Training of Deep Neural Networks

VESELÝ, K. HANNEMANN, M. BURGET, L.

Originální název

Semi-supervised Training of Deep Neural Networks

Anglický název

Semi-supervised Training of Deep Neural Networks

Jazyk

en

Originální abstrakt

Our quest in this paper is to search for an optimal dataselection strategy for the semi-supervised DNN training. We performed an analysis at all the three stages of DNN training.

Anglický abstrakt

Our quest in this paper is to search for an optimal dataselection strategy for the semi-supervised DNN training. We performed an analysis at all the three stages of DNN training.

Dokumenty

BibTex 


@inproceedings{BUT105976,
  author="Karel {Veselý} and Mirko {Hannemann} and Lukáš {Burget}",
  title="Semi-supervised Training of Deep Neural Networks",
  annote="Our quest in this paper is to search for an optimal dataselection strategy for
the semi-supervised DNN training. We performed an analysis at all the three
stages of DNN training.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of ASRU 2013",
  chapter="105976",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2013",
  month="december",
  pages="267--272",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}