Journal article · 2017 · Open access

Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets

Vadim V. Romanuke

Applied Computer Systems, 22(1), 54–63 · Published 1 December 2017 · DOI 10.1515/acss-2017-0018

Open PDFView at the publisherCite this paper

In brief

“Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets” is a 2017 journal article by Vadim V. Romanuke, published in Applied Computer Systems. OpenAlex counts 13 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Applied Computer Systems.

Citations
13
Most cited in
2022 (5)
Field-weighted impact
0.60
References
18
Authors
1

Abstract

A technique of DropOut for preventing overfitting of convolutional neural networks for image classification is considered in the paper. The goal is to find a rule of rationally allocating DropOut layers of 0.5 rate to maximise performance. To achieve the goal, two common network architectures are used having either 4 or 5 convolutional layers. Benchmarking is fulfilled with CIFAR-10, EEACL26, and NORB datasets. Initially, series of all admissible versions for allocation of DropOut layers are generated. After the performance against the series is evaluated, normalized and averaged, the compromising rule is found. It consists in non-compactly inserting a few DropOut layers before the last convolutional layer. It is likely that the scheme with two or more DropOut layers fits networks of many convolutional layers for image classification problems with a plenty of features. Such a scheme shall also fit simple datasets prone to overfitting. In fact, the rule “prefers” a fewer number of DropOut layers. The exemplary gain of the rule application is roughly between 10 % and 50 %.

Cite this paper

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

APA 7

Romanuke, V. V. (2017). Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets. Applied Computer Systems, 22(1), 54–63. https://doi.org/10.1515/acss-2017-0018

MLA 9

Romanuke, Vadim V. “Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets.” Applied Computer Systems, vol. 22, no. 1, 2017, pp. 54–63. https://doi.org/10.1515/acss-2017-0018.

Chicago

Romanuke, Vadim V. 2017. “Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets.” Applied Computer Systems 22 (1): 54–63. https://doi.org/10.1515/acss-2017-0018.

Harvard

Romanuke, V. V. (2017) ‘Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets’, Applied Computer Systems, 22(1), pp. 54–63. doi:10.1515/acss-2017-0018.

IEEE

V. V. Romanuke, “Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets,” Applied Computer Systems, vol. 22, no. 1, pp. 54–63, 2017, doi: 10.1515/acss-2017-0018.

BibTeX

@article{romanuke2017appropriateness,
  title     = {{Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets}},
  author    = {Romanuke, Vadim V.},
  journal   = {Applied Computer Systems},
  year      = {2017},
  volume    = {22},
  number    = {1},
  pages     = {54--63},
  doi       = {10.1515/acss-2017-0018},
  url       = {https://doi.org/10.1515/acss-2017-0018}
}

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

Citations by year

YearCitationsShare of the best year
201844
201922
202011
202111
202255

Its field-weighted citation impact is 0.60: it has been cited 0.60 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 › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • dropout
  • convolutional neural networks
  • overfitting
  • image classification
  • CIFAR-10
  • network architecture

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?

Romanuke, V. V. (2017). Appropriateness of Dropout Layers and Allocation of Their 0.5 Rates across Convolutional Neural Networks for CIFAR-10, EEACL26, and NORB Datasets. Applied Computer Systems, 22(1), 54–63. https://doi.org/10.1515/acss-2017-0018

How many times has this paper been cited?

13 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Applied Computer Systems: sign in and open the PDF from this page.

Who wrote this paper?

Vadim V. Romanuke.

What is the DOI of this paper?

10.1515/acss-2017-0018, permanently at https://doi.org/10.1515/acss-2017-0018. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.