A general framework for neural delay differential equations with various delay types
Chaos: An Interdisciplinary Journal of Nonlinear Science · 01.05.2026 · 36 (5)
DOI: 10.1063/5.0325998 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos: An Interdisciplinary Journal of Nonlinear Science, online erschienen am 04.05.2026. Verfasst von Jiaxuan Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematical Sciences, Fudan University, Shanghai 200433, China. Die Arbeit nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shanghai Municipality, SMEC.
Abstract (Originalsprache)
This work proposes a general framework for Neural Delay Differential Equations (NDDEs), a class of continuous-depth neural networks, namely, the Generalized NDDEs (GNDDEs), incorporating various types of delays beyond the previously considered constant delays, including time-dependent, state-dependent, and time-state-dependent delays. Furthermore, we employ a simulation-free training strategy for the vector field, allowing the system reconstruction directly from the irregularly sampled time series without the prior model knowledge. Specifically, we perform the regression between the preprocessed target and parameterized vector fields, bypassing the need to numerically solve the differential equations as required in conventional time-series regression. Additionally, GNDDEs enable adaptive, model-free identification of the delay functions, along with the model-based identification of the system parameters. The experimental results demonstrate that the proposed framework exhibits the notable effectiveness and computational efficiency across a variety of delay differential equation problems, further broadening the applicability of continuous-depth neural networks in the delay system modeling.
Autor:innen und Institutionen
- School of Mathematical Sciences, Fudan University, Shanghai 200433, China.
- Research Institute of Intelligent Complex Systems, Fudan University, Shanghai 200433, China.
- MOE Frontiers Center for Brain Science and State Key Laboratory of Medical Neurobiology, Fudan University, Shanghai 200032, China.
- Shanghai Artificial Intelligence Laboratory, Shanghai 200232, China.
- School of Mathematical Sciences, SCMS, SCAM, and CCSB, Fudan University, Shanghai 200433, China.
ORCID-Profile: Jiaxuan Zhang, Qunxi Zhu, Wei Lin
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shanghai Municipality
- SMEC
- National Key R&D Program of China
Zitieren
APA
Zhang, J., Zhu, Q., & Lin, W. (2026). A general framework for neural delay differential equations with various delay types. Chaos: An Interdisciplinary Journal of Nonlinear Science, 36(5). https://doi.org/10.1063/5.0325998
Vancouver
Zhang J, Zhu Q, Lin W. A general framework for neural delay differential equations with various delay types. Chaos: An Interdisciplinary Journal of Nonlinear Science. 2026;36(5). doi:10.1063/5.0325998
BibTeX
@article{Zhang2026,
author = {Zhang, Jiaxuan and Zhu, Qunxi and Lin, Wei},
title = {A general framework for neural delay differential equations with various delay types},
journal = {Chaos: An Interdisciplinary Journal of Nonlinear Science},
year = {2026},
volume = {36},
number = {5},
doi = {10.1063/5.0325998}
}
EUVIMED