Assessing Four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
Journal of Computer Science Research · 29.07.2024 · 6 (3) · 17-22
DOI: 10.30564/jcsr.v6i3.6804 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science Research, online erschienen am 29.07.2024. Verfasst von Feiyang Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Although the image recognition has been a research topic for many years, many researchers still have a keen interest in it. In some papers, however, there is a tendency to compare models only on one or two datasets, either because of time restraints or because the model is tailored to a specific task. Accordingly, it is hard to understand how well a certain model generalizes across image recognition field. In this paper, we compare four neural networks on MNIST dataset with different division. Among of them, three are Convolutional Neural Networks (CNN), Deep Residual Network (ResNet) and Dense Convolutional Network (DenseNet) respectively, and the other is our improvement on CNN baseline through introducing Capsule Network (CapsNet) to image recognition area. We show that the previous models despite do a quite good job in this area, our retrofitting can be applied to get a better performance. The result obtained by CapsNet is an accuracy rate of 99.75%, and it is the best result published so far. Another inspiring result is that CapsNet only needs a small amount of data to get the excellent performance. Finally, we will apply CapsNet's ability to generalize in other image recognition field in the future.
Zitieren
APA
Chen, F., Luo, Z., Chen, N., Mao, H., Hu, H., Jiang, Y., Pan, X., & Zhang, H. (2024). Assessing Four Neural Networks on Handwritten Digit Recognition Dataset (MNIST). Journal of Computer Science Research, 6(3), 17-22. https://doi.org/10.30564/jcsr.v6i3.6804
Vancouver
Chen F, Luo Z, Chen N, Mao H, Hu H, Jiang Y, et al. Assessing Four Neural Networks on Handwritten Digit Recognition Dataset (MNIST). Journal of Computer Science Research. 2024;6(3):17-22. doi:10.30564/jcsr.v6i3.6804
BibTeX
@article{Chen2024,
author = {Chen, Feiyang and Luo, Ziqian and Chen, Nan and Mao, Hanyang and Hu, Hanlin and Jiang, Ying and Pan, Xueting and Zhang, Huitao},
title = {Assessing Four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)},
journal = {Journal of Computer Science Research},
year = {2024},
volume = {6},
number = {3},
pages = {17--22},
doi = {10.30564/jcsr.v6i3.6804}
}
EUVIMED