EUVIMEDEUVIMED entdecken
Crossref

8 Bit Quantized Neural Network

P Amudha, Shyadha Fathima J, Tarakeshwari S N, Thansika K

INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 21.04.2026 · 10 (04) · 1-9

DOI: 10.55041/ijsrem60754 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, online erschienen am 21.04.2026. Verfasst von P Amudha und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

- Efficient deployment of deep neural networks on edge devices is constrained by limited computational resources, memory, and energy availability. While full-precision (FP32) models provide high accuracy, their resource demands hinder practical edge implementation. This paper evaluates 8-bit integer (INT8) quantization using Quantization-Aware Training (QAT) on the ResNet-18 architecture with the CIFAR-10 dataset. By modeling quantization effects during training, the approach reduces the accuracy loss typically associated with lower precision. Experimental results show that the INT8 model achieves 94.77% accuracy, closely matching the FP32 baseline of 94.79%, while significantly improving efficiency in terms of model size and computation. These findings demonstrate that INT8 quantization offers an effective trade-off between performance and resource utilization for real-time edge AI applications. KeyWords: Edge Computing, Model Quantization, Quantization-Aware Training, ResNet-18, Low-Precision Neural Networks, Embedded AI.

Zitieren

APA

Amudha, P., J, S. F., N, T. S., & K, T. (2026). 8 Bit Quantized Neural Network. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, 10(04), 1-9. https://doi.org/10.55041/ijsrem60754

Vancouver

Amudha P, J SF, N TS, K T. 8 Bit Quantized Neural Network. INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT. 2026;10(04):1-9. doi:10.55041/ijsrem60754

BibTeX
@article{Amudha2026,
  author = {Amudha, P and J, Shyadha Fathima and N, Tarakeshwari S and K, Thansika},
  title = {8 Bit Quantized Neural Network},
  journal = {INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT},
  year = {2026},
  volume = {10},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijsrem60754}
}
Kostenlos starten →