Journal article · 2025 · Open access

Function and Accuracy of Neural Network Based on Different Hyper-parameters

Siyuan Chen, Yijin Guo

Applied and Computational Engineering, 131(1), 123–131 · Published 24 January 2025 · DOI 10.54254/2755-2721/2024.20573

Open PDFView at the publisherCite this paper

In brief

“Function and Accuracy of Neural Network Based on Different Hyper-parameters” is a 2025 journal article by Siyuan Chen and Yijin Guo, published in Applied and Computational Engineering. OpenAlex counts 1 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Applied and Computational Engineering.

Citations
1
Most cited in
2025 (1)
Field-weighted impact
0.19
References
14
Authors
2

Abstract

This study explores the application of deep learning in image classification, with a particular focus on the overfitting problem and its solutions. The performance of Convolutional Neural Network (CNN) and Fully Connected Neural Network (FCN) in animal image classification tasks was compared experimentally. Experimental results show that the CNN model has higher accuracy and robustness than the FCN model when dealing with practical challenges such as diversification, illumination variation and image blurring. In addition, this study also explored the effects of early stop and dropout techniques in reducing overfitting, and found that an appropriate dropout ratio can significantly improve the generalization ability of the model. Finally, the generalization ability of the model is verified by testing on the Stanford pets image dataset, and suggestions for future research directions are put forward.

Cite this paper

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

APA 7

Chen, S., & Guo, Y. (2025). Function and Accuracy of Neural Network Based on Different Hyper-parameters. Applied and Computational Engineering, 131(1), 123–131. https://doi.org/10.54254/2755-2721/2024.20573

MLA 9

Chen, Siyuan, and Yijin Guo. “Function and Accuracy of Neural Network Based on Different Hyper-parameters.” Applied and Computational Engineering, vol. 131, no. 1, 2025, pp. 123–131. https://doi.org/10.54254/2755-2721/2024.20573.

Chicago

Chen, Siyuan and Yijin Guo. 2025. “Function and Accuracy of Neural Network Based on Different Hyper-parameters.” Applied and Computational Engineering 131 (1): 123–131. https://doi.org/10.54254/2755-2721/2024.20573.

Harvard

Chen, S. and Guo, Y. (2025) ‘Function and Accuracy of Neural Network Based on Different Hyper-parameters’, Applied and Computational Engineering, 131(1), pp. 123–131. doi:10.54254/2755-2721/2024.20573.

IEEE

S. Chen and Y. Guo, “Function and Accuracy of Neural Network Based on Different Hyper-parameters,” Applied and Computational Engineering, vol. 131, no. 1, pp. 123–131, 2025, doi: 10.54254/2755-2721/2024.20573.

BibTeX

@article{chen2025function,
  title     = {{Function and Accuracy of Neural Network Based on Different Hyper-parameters}},
  author    = {Chen, Siyuan and Guo, Yijin},
  journal   = {Applied and Computational Engineering},
  year      = {2025},
  volume    = {131},
  number    = {1},
  pages     = {123--131},
  doi       = {10.54254/2755-2721/2024.20573},
  url       = {https://doi.org/10.54254/2755-2721/2024.20573}
}

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

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • convolutional neural networks
  • fully connected neural network
  • animal image classification
  • overfitting
  • dropout
  • early stopping
  • hyperparameter optimization
  • generalization

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?

Chen, S., & Guo, Y. (2025). Function and Accuracy of Neural Network Based on Different Hyper-parameters. Applied and Computational Engineering, 131(1), 123–131. https://doi.org/10.54254/2755-2721/2024.20573

How many times has this paper been cited?

1 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 and Computational Engineering: sign in and open the PDF from this page.

Who wrote this paper?

Siyuan Chen, Yijin Guo.

What is the DOI of this paper?

10.54254/2755-2721/2024.20573, permanently at https://doi.org/10.54254/2755-2721/2024.20573. 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.