Improving deep neural networks for LVCSR using rectified linear units and dropout

@article{Dahl2013ImprovingDN,
  title={Improving deep neural networks for LVCSR using rectified linear units and dropout},
  author={George E. Dahl and Tara N. Sainath and Geoffrey E. Hinton},
  journal={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2013},
  pages={8609-8613}
}
Recently, pre-trained deep neural networks (DNNs) have outperformed traditional acoustic models based on Gaussian mixture models (GMMs) on a variety of large vocabulary speech recognition benchmarks. Deep neural nets have also achieved excellent results on various computer vision tasks using a random “dropout” procedure that drastically improves generalization error by randomly omitting a fraction of the hidden units in all layers. Since dropout helps avoid over-fitting, it has also been… CONTINUE READING
Highly Influential
This paper has highly influenced 29 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 760 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 401 extracted citations

760 Citations

050100150'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 760 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 21 references

, Brian Kingsbury , and Bhuvana Ramab - hadran , “ Auto - Encoder Bottleneck Features Using Deep Belief Networks

  • Tara N. Sainath
  • Proc . ICASSP
  • 2012

, Nitish Srivastava , Alex Krizhevsky , Ilya Sutskever , and Ruslan Salakhutdinov , “ Improving neural networks by preventing co - adaptation of feature detectors

  • Geoffrey E. Hinton, Li Deng, Dong Yu, George E. Dahl, Patrick Nguyen, Tara N. Sainath
  • The Computing Research Repository
  • 2012

, and Bhuvana Ramabhadran , “ AutoEncoder Bottleneck Features Using Deep Belief Networks

  • Tara N. Sainath, Brian Kingsbury
  • 2012

Similar Papers

Loading similar papers…