Deep Neural Networks Inspired by Differential Equations
ACM Computing Surveys · 31.10.2026 · 58 (14) · 1-37
DOI: 10.1145/3828753 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 28.07.2026. Verfasst von Yongshuai Liu und 8 weiteren Autor:innen. Die Arbeit nennt 284 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National () NSFC.
Abstract (Originalsprache)
Deep learning has emerged as an important technology in fields such as computer vision, scientific computing, and dynamical systems, thereby driving major advancements across these domains. However, neural networks persistently face challenges related to theoretical understanding, interpretability, and generalization. Thus, researchers are increasingly adopting a differential equations perspective to propose a unified theoretical framework and systematic design methodologies. We establish a comprehensive taxonomy of the literature from two distinct perspectives. First, we classify the models based on their mathematical formulations, covering ordinary, partial, and stochastic differential equations (ODEs, PDEs, and SDEs). Second, we categorize them by their methodological roles, distinguishing between equation-guided networks and networks designed for solving equations. Moreover, we conduct a qualitative meta-analysis supported by consolidated evidence summaries from existing literature to illustrate their characteristics and performance. Finally, we explore promising research directions in integrating differential equations with deep learning to offer new insights for developing computational methods with improved interpretability and generalization.
Förderung
- National () NSFC
Zitieren
APA
Liu, Y., Wang, L., Qin, K., Zhang, Q., Wang, F., Cui, L., Liu, J., Duan, Y., & Zeng, T. (2026). Deep Neural Networks Inspired by Differential Equations. ACM Computing Surveys, 58(14), 1-37. https://doi.org/10.1145/3828753
Vancouver
Liu Y, Wang L, Qin K, Zhang Q, Wang F, Cui L, et al. Deep Neural Networks Inspired by Differential Equations. ACM Computing Surveys. 2026;58(14):1-37. doi:10.1145/3828753
BibTeX
@article{Liu2026,
author = {Liu, Yongshuai and Wang, Lianfang and Qin, Kuilin and Zhang, Qinghua and Wang, Faqiang and Cui, Li and Liu, Jun and Duan, Yuping and Zeng, Tieyong},
title = {Deep Neural Networks Inspired by Differential Equations},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {14},
pages = {1--37},
doi = {10.1145/3828753}
}
EUVIMED