Investigation of the Impact of Hyperparameters on the Accuracy of Neural Network Predictions Using the Fashion-MNIST Dataset
https://doi.org/10.35596/1729-7648-2026-32-2-44-52
Abstract
Machine learning and artificial intelligence (AI) are currently actively researching methods for optimizing and tuning model hyperparameters. One key area of research is analyzing the impact of varying hyperparameters, such as the number of two-dimensional convolution (Conv2D) layers and their parameters (number of filters, kernel size), the size and stride of maximum pooling (MaxPooling2D) layers, the number of neurons in fully connected layers, activation functions, batch size (batch_size), and the number of training epochs, on the prediction accuracy of machine learning models using a convolutional neural network architecture on the Fashion-MNIST
About the Authors
D. Klimenka
Belarusian State University
Belarus
Belarus
Klimenka D., Studen
220064, Minsk, Kurchatova St., 5;
Tel.: +375 17 209-58-36
А. Kazlova
Belarusian State University
Belarus
Belarus
Kazlova A., Cand. Sci. (Phys. and Math.) Associate Professor, Head of the Department of Intelligent Systems
220064, Minsk, Kurchatova St., 5;
Tel.: +375 17 209-58-36
References
1. Kleiner, S. G. (2025) Study of the Accuracy of Solving a Hyper Parameter Optimization Problem Using a Neural Network. Available: https://www.xn8sbempclcwd3bmt.xnp1ai/article/24427 (Accessed 24 December 2025) (in Russian).
2. Ignatieva S. A. (2025) The Impact of Hyper Parameter Selection in Convolutional Neural Network Training on the Accuracy of Person Re-Identification in Video Surveillance Systems. Available: https://elib.psu.by/bitstream/123456789/34506/1/163-167.pdf (Accessed 24 December 2025) (in Russian).
3. Fashion MNIST. Available: https://github.com/zalandoresearch/fashion-mnist (Accessed 24 December 2025) (in Russian).
4. Alzubaidi L., Zhang J., Humaidi A. J., Al-Dujaili A., Duan Ye, Al-Shamma O., et al. (2021) Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions. Journal of Big Data. 8 (53), 2–74. https://doi.org/10.1186/s40537-021-00444-8.
5. Murphy K. P. (2022) Probabilistic Machine Learning: An Introduction. USA, MIT Press Publ. 323–358.
Review
For citations:
Klimenka D., Kazlova А. Investigation of the Impact of Hyperparameters on the Accuracy of Neural Network Predictions Using the Fashion-MNIST Dataset. Digital Transformation. 2026;32(2):44-52. (In Russ.) https://doi.org/10.35596/1729-7648-2026-32-2-44-52
Views:
47
JATS XML
Email this article 