Method for Preparing Convolutional Neural Networks for Edge Deployment
Electronics and Control Systems · 11.02.2026 · 1 (87) · 9-13
DOI: 10.18372/1990-5548.87.20773 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics and Control Systems, online erschienen am 11.02.2026. Verfasst von Dmytro Prochukhan.
Abstract (Originalsprache)
This study addresses the critical problem of accuracy loss during the compression of deep neural networks for mobile platforms. The research focuses on optimizing convolutional neural networks for operation under constrained hardware resources and the Memory Wall effect. An innovative Edge-deployment preparation method is proposed, which, unlike traditional sequential approaches, integrates structured pruning, post-training quantization, and a fine-tuning stage into a single iterative cycle. This approach provides a synergistic effect, minimizing accuracy degradation while achieving maximum parameter compression. Comparative analysis results confirm that the developed method meets strict latency and power consumption constraints, which are vital for mobile diagnostics in medical applications. Future research prospects involve adapting this method to other machine learning architectures.
Zitieren
APA
Prochukhan, D. (2026). Method for Preparing Convolutional Neural Networks for Edge Deployment. Electronics and Control Systems, 1(87), 9-13. https://doi.org/10.18372/1990-5548.87.20773
Vancouver
Prochukhan D. Method for Preparing Convolutional Neural Networks for Edge Deployment. Electronics and Control Systems. 2026;1(87):9-13. doi:10.18372/1990-5548.87.20773
BibTeX
@article{Prochukhan2026,
author = {Prochukhan, Dmytro},
title = {Method for Preparing Convolutional Neural Networks for Edge Deployment},
journal = {Electronics and Control Systems},
year = {2026},
volume = {1},
number = {87},
pages = {9--13},
doi = {10.18372/1990-5548.87.20773}
}
EUVIMED