Paper · 2014

Dropout: a simple way to prevent neural networks from overfitting

Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov

http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf, 15(1), 1929–1958 · Published 1 January 2014

View at the publisherCite this paper

In brief

“Dropout: a simple way to prevent neural networks from overfitting” is a 2014 paper by Nitish Srivastava and 4 co-authors, published in http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf. OpenAlex counts 33,578 citations as of 15 November 2026, which puts it in the top 3% of works published in 2014 by citations. The publisher's version is not open access, and OpenAlex records no free legal copy.

Citations
33,578
Most cited in
2021 (5,230)
Field-weighted impact
869.03
References
35
Authors
5

Abstract

Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique… Read the full abstract at the publisher.

Excerpt. This paper is not open access.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Srivastava, N., Hinton, G. E., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf, 15(1), 1929–1958. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.8604

MLA 9

Srivastava, Nitish, et al. “Dropout: a simple way to prevent neural networks from overfitting.” http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf, vol. 15, no. 1, 2014, pp. 1929–1958. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.8604.

Chicago

Srivastava, Nitish, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. “Dropout: a simple way to prevent neural networks from overfitting.” http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf 15 (1): 1929–1958. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.8604.

Harvard

Srivastava, N. et al. (2014) ‘Dropout: a simple way to prevent neural networks from overfitting’, http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf, 15(1), pp. 1929–1958. Available at: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.8604.

IEEE

N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting,” http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf, vol. 15, no. 1, pp. 1929–1958, 2014.

BibTeX

@article{srivastava2014dropout,
  title     = {{Dropout: a simple way to prevent neural networks from overfitting}},
  author    = {Srivastava, Nitish and Hinton, Geoffrey E. and Krizhevsky, Alex and Sutskever, Ilya and Salakhutdinov, Ruslan},
  journal   = {http://www.cs.toronto.edu/\%7Ersalakhu/papers/srivastava14a.pdf},
  year      = {2014},
  volume    = {15},
  number    = {1},
  pages     = {1929--1958},
  url       = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.8604}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20172,1802180
20183,6953695
20195,0805080
20205,0765076
20215,2305230
20223,6063606
20233,1143114
20242,6042604
20251,5731573
20263838

Its field-weighted citation impact is 869.03: it has been cited 869.03 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications

  • dropout
  • overfitting
  • regularization
  • deep neural network
  • ensemble averaging
  • supervised learning
  • vision
  • speech recognition

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Srivastava, N., Hinton, G. E., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. http://www.cs.toronto.edu/%7Ersalakhu/papers/srivastava14a.pdf, 15(1), 1929–1958. http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.8604

How many times has this paper been cited?

33,578 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

OpenAlex records no free legal copy. Check your library's access, the authors' pages or a repository, or ask the corresponding author for a copy.

Who wrote this paper?

Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.