A Survey of Loss Functions in Deep Learning
Mathematics · 27.07.2025 · 13 (15) · 2417
DOI: 10.3390/math13152417 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 27.07.2025. Verfasst von Caiyi Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 106 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Changsha, National Key Laboratory of Security Communication Foundation.
Abstract (Originalsprache)
Deep learning (DL), as a cutting-edge technology in artificial intelligence, has significantly impacted fields such as computer vision and natural language processing. Loss function determines the convergence speed and accuracy of the DL model and has a crucial impact on algorithm quality and model performance. However, most of the existing studies focus on the improvement of specific problems of loss function, which lack a systematic summary and comparison, especially in computer vision and natural language processing tasks. Therefore, this paper reclassifies and summarizes the loss functions in DL and proposes a new category of metric loss. Furthermore, this paper conducts a fine-grained division of regression loss, classification loss, and metric loss, elaborating on the existing problems and improvements. Finally, the new trend of compound loss and generative loss is anticipated. The proposed paper provides a new perspective for loss function division and a systematic reference for researchers in the DL field.
Förderung
- Natural Science Foundation of Changsha
- National Key Laboratory of Security Communication Foundation
Zitieren
APA
Li, C., Liu, K., & Liu, S. (2025). A Survey of Loss Functions in Deep Learning. Mathematics, 13(15), 2417. https://doi.org/10.3390/math13152417
Vancouver
Li C, Liu K, Liu S. A Survey of Loss Functions in Deep Learning. Mathematics. 2025;13(15):2417. doi:10.3390/math13152417
BibTeX
@article{Li2025,
author = {Li, Caiyi and Liu, Kaishuai and Liu, Shuai},
title = {A Survey of Loss Functions in Deep Learning},
journal = {Mathematics},
year = {2025},
volume = {13},
number = {15},
pages = {2417},
doi = {10.3390/math13152417}
}
EUVIMED