EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CLOS network: A parameter-efficient alternative to linear layers in neural networks

Orgil Jargalsaikhan, Magvan-Erdene Gantulga, Nomin-Erdene Zorigtbaatar, Battsetseg Erdenebat

ICT Focus · 31.12.2025 · 4 (1)

DOI: 10.58873/sict.v4i1.45 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ICT Focus, online erschienen am 31.12.2025. Verfasst von Orgil Jargalsaikhan und 3 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose utilizing the CLOS network architecture to replace traditional linear layers in deep learning models including transformers. The CLOS network, commonly used in networking systems, is adapted to neural networks to reduce parameter sizes while maintaining model performance. Our experiments show that the CLOS network achieves the same accuracy and loss as the conventional linear layer, but with fewer parameters. However, this efficiency comes at the cost of increased processing time which is 1.5x to 3x slower. Despite this trade-off, the CLOS network can be an effective alternative for parameter reduction in various architectures, including large models like transformers.

Zitieren

APA

Jargalsaikhan, O., Gantulga, M., Zorigtbaatar, N., & Erdenebat, B. (2025). CLOS network: A parameter-efficient alternative to linear layers in neural networks. ICT Focus, 4(1). https://doi.org/10.58873/sict.v4i1.45

Vancouver

Jargalsaikhan O, Gantulga M, Zorigtbaatar N, Erdenebat B. CLOS network: A parameter-efficient alternative to linear layers in neural networks. ICT Focus. 2025;4(1). doi:10.58873/sict.v4i1.45

BibTeX
@article{Jargalsaikhan2025,
  author = {Jargalsaikhan, Orgil and Gantulga, Magvan-Erdene and Zorigtbaatar, Nomin-Erdene and Erdenebat, Battsetseg},
  title = {CLOS network: A parameter-efficient alternative to linear layers in neural networks},
  journal = {ICT Focus},
  year = {2025},
  volume = {4},
  number = {1},
  doi = {10.58873/sict.v4i1.45}
}
Kostenlos starten →