Journal article · 2025 · Open access

Dropout: An Effective Approach to Prevent Neural Networks from Overfitting

Shahwan Younis Ali, Hajar Maseeh Yasin

Asian Journal of Research in Computer Science, 18(2), 163–185 · Published 4 February 2025 · DOI 10.9734/ajrcos/2025/v18i2569

Open full textCite this paper

In brief

“Dropout: An Effective Approach to Prevent Neural Networks from Overfitting” is a 2025 journal article by Shahwan Younis Ali and Hajar Maseeh Yasin, published in Asian Journal of Research in Computer Science. OpenAlex counts 21 citations as of 18 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access: the full text is free to read at Asian Journal of Research in Computer Science.

Citations
21
Most cited in
2026 (13)
Field-weighted impact
4.00
Authors
2

Abstract

Overfitting remains a significant challenge in training neural networks, often leading to poor generalization on unseen data. Dropout has emerged as a powerful regularization technique to mitigate overfitting by randomly deactivating neurons during training, thereby preventing co-adaptation of features and encouraging diverse representations. This paper explores the theoretical foundations and practical implementations of dropout across various neural network architectures, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). Through empirical analysis on benchmark datasets such as CIFAR-10, MNIST, and others, dropout is shown to improve model robustness and accuracy significantly. The study also compares dropout with alternative regularization methods, such as weight constraints and batch normalization, highlighting its effectiveness in diverse scenarios. Despite its success, dropout's performance is influenced by hyperparameter tuning and dataset characteristics. The paper concludes by discussing limitations, such as computational overhead, and proposes directions for optimizing dropout for specific applications, including dynamic dropout rates and hybrid regularization techniques.

Cite this paper

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

APA 7

Ali, S. Y., & Yasin, H. M. (2025). Dropout: An Effective Approach to Prevent Neural Networks from Overfitting. Asian Journal of Research in Computer Science, 18(2), 163–185. https://doi.org/10.9734/ajrcos/2025/v18i2569

MLA 9

Ali, Shahwan Younis, and Hajar Maseeh Yasin. “Dropout: An Effective Approach to Prevent Neural Networks from Overfitting.” Asian Journal of Research in Computer Science, vol. 18, no. 2, 2025, pp. 163–185. https://doi.org/10.9734/ajrcos/2025/v18i2569.

Chicago

Ali, Shahwan Younis and Hajar Maseeh Yasin. 2025. “Dropout: An Effective Approach to Prevent Neural Networks from Overfitting.” Asian Journal of Research in Computer Science 18 (2): 163–185. https://doi.org/10.9734/ajrcos/2025/v18i2569.

Harvard

Ali, S. Y. and Yasin, H. M. (2025) ‘Dropout: An Effective Approach to Prevent Neural Networks from Overfitting’, Asian Journal of Research in Computer Science, 18(2), pp. 163–185. doi:10.9734/ajrcos/2025/v18i2569.

IEEE

S. Y. Ali and H. M. Yasin, “Dropout: An Effective Approach to Prevent Neural Networks from Overfitting,” Asian Journal of Research in Computer Science, vol. 18, no. 2, pp. 163–185, 2025, doi: 10.9734/ajrcos/2025/v18i2569.

BibTeX

@article{ali2025dropout,
  title     = {{Dropout: An Effective Approach to Prevent Neural Networks from Overfitting}},
  author    = {Ali, Shahwan Younis and Yasin, Hajar Maseeh},
  journal   = {Asian Journal of Research in Computer Science},
  year      = {2025},
  volume    = {18},
  number    = {2},
  pages     = {163--185},
  doi       = {10.9734/ajrcos/2025/v18i2569},
  url       = {https://doi.org/10.9734/ajrcos/2025/v18i2569}
}

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

Topic and keywords

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

  • dropout
  • overfitting
  • neural network regularization
  • generalization
  • convolutional neural networks
  • recurrent neural networks
  • batch normalization
  • weight restrictions

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?

Ali, S. Y., & Yasin, H. M. (2025). Dropout: An Effective Approach to Prevent Neural Networks from Overfitting. Asian Journal of Research in Computer Science, 18(2), 163–185. https://doi.org/10.9734/ajrcos/2025/v18i2569

How many times has this paper been cited?

21 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 Asian Journal of Research in Computer Science: sign in and open the full text from this page.

Who wrote this paper?

Shahwan Younis Ali, Hajar Maseeh Yasin.

What is the DOI of this paper?

10.9734/ajrcos/2025/v18i2569, permanently at https://doi.org/10.9734/ajrcos/2025/v18i2569. 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.