Deep Neural Networks Inspired by Differential Equations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908587297603584 |
|---|---|
| author | Liu, Yongshuai Wang, Lianfang Qin, Kuilin Zhang, Qinghua Wang, Faqiang Cui, Li Liu, Jun Duan, Yuping Zeng, Tieyong |
| author_facet | Liu, Yongshuai Wang, Lianfang Qin, Kuilin Zhang, Qinghua Wang, Faqiang Cui, Li Liu, Jun Duan, Yuping Zeng, Tieyong |
| contents | Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challenges related to theoretical understanding, interpretability, and generalization. To address these issues, researchers are increasingly adopting a differential equations perspective to propose a unified theoretical framework and systematic design methodologies for neural networks. In this paper, we provide an extensive review of deep neural network architectures and dynamic modeling methods inspired by differential equations. We specifically examine deep neural network models and deterministic dynamical network constructs based on ordinary differential equations (ODEs), as well as regularization techniques and stochastic dynamical network models informed by stochastic differential equations (SDEs). We present numerical comparisons of these models 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 intelligent computational methods that boast enhanced interpretability and generalization capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09685 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deep Neural Networks Inspired by Differential Equations Liu, Yongshuai Wang, Lianfang Qin, Kuilin Zhang, Qinghua Wang, Faqiang Cui, Li Liu, Jun Duan, Yuping Zeng, Tieyong Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Numerical Analysis A.1; I.2; I.4 Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challenges related to theoretical understanding, interpretability, and generalization. To address these issues, researchers are increasingly adopting a differential equations perspective to propose a unified theoretical framework and systematic design methodologies for neural networks. In this paper, we provide an extensive review of deep neural network architectures and dynamic modeling methods inspired by differential equations. We specifically examine deep neural network models and deterministic dynamical network constructs based on ordinary differential equations (ODEs), as well as regularization techniques and stochastic dynamical network models informed by stochastic differential equations (SDEs). We present numerical comparisons of these models 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 intelligent computational methods that boast enhanced interpretability and generalization capabilities. |
| title | Deep Neural Networks Inspired by Differential Equations |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Numerical Analysis A.1; I.2; I.4 |
| url | https://arxiv.org/abs/2510.09685 |