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
Applied Computer Systems, 22(1), 54–63 · Published 1 December 2017 · DOI 10.1515/acss-2017-0018
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
| Year | Citations | Share of the best year |
|---|---|---|
| 2018 | 4 | |
| 2019 | 2 | |
| 2020 | 1 | |
| 2021 | 1 | |
| 2022 | 5 |
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
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
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.