EUVIMEDEUVIMED entdecken
Crossref

Transfer learning in neural networks: leveraging pre-trained models for improved performance

Abdul Sttar Ismail Wdaa, Iraq Ali Hussein, Ali Azeez Ahmed

Future Technology · 15.08.2026 · 5 (3) · 309-318

DOI: 10.55670/fpll.futech.5.3.27 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Technology, online erschienen am 15.08.2026. Verfasst von Abdul Sttar Ismail Wdaa und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transfer learning has become a key technique for improving the accuracy of neural networks in low-resource, low-data environments. The quantitative comparative analysis of the pre-trained models includes ResNet50, VGG16, BERT, GPT, and the baseline CNN and LSTM models. They are compared across three different application areas: computer vision, natural language processing (NLP), and medical imaging. The five benchmark datasets used were ImageNet, CIFAR-10, SST-2, IMDB, and Chest X-Ray. All experiments used the same preprocessing pipeline and evaluation metrics (accuracy, F1 score, precision, recall, and ROC-AUC). Results showed that models trained on the pre-trained data achieved consistently greater accuracy than the baselines in all domains (9-20%) and F1-score (0.09-0.16) gains. ResNet50 achieved 92% accuracy on CIFAR-10, compared to 72% for the CNN baseline, whereas BERT hit 92% on SST-2, with 80% accuracy for LSTM. VGG16 improved the accuracy of Chest X-Ray classification from 78% to 87% and reduced training time by up to 60%. There were a few instances of minor overfitting and domain mismatch, emphasizing the need for adaptive fine-tuning strategies. The results demonstrate that transfer learning significantly improves convergence speed, generalization, and computational efficiency, making it a promising approach for AI applications across domains such as healthcare, NLP, and autonomous systems.

Zitieren

APA

Wdaa, A. S. I., Hussein, I. A., & Ahmed, A. A. (2026). Transfer learning in neural networks: leveraging pre-trained models for improved performance. Future Technology, 5(3), 309-318. https://doi.org/10.55670/fpll.futech.5.3.27

Vancouver

Wdaa ASI, Hussein IA, Ahmed AA. Transfer learning in neural networks: leveraging pre-trained models for improved performance. Future Technology. 2026;5(3):309-318. doi:10.55670/fpll.futech.5.3.27

BibTeX
@article{Wdaa2026,
  author = {Wdaa, Abdul Sttar Ismail and Hussein, Iraq Ali and Ahmed, Ali Azeez},
  title = {Transfer learning in neural networks: leveraging pre-trained models for improved performance},
  journal = {Future Technology},
  year = {2026},
  volume = {5},
  number = {3},
  pages = {309--318},
  doi = {10.55670/fpll.futech.5.3.27}
}
Kostenlos starten →