Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Neural ordinary differential equations (neural ODEs) are a well-established tool for optimizing the parameters of dynamical systems, with applications in image classification, optimal control, and physics learning. Although dynamical systems of interest often evolve on Lie groups and more general differentiable manifolds, theoretical results for neural ODEs are frequently phrased on Rn. We collect recent results for neural ODEs on manifolds and present a unifying derivation of various results that serves as a tutorial to extend existing methods to differentiable manifolds. We also extend the results to the recent class of neural ODEs on Lie groups, highlighting a non-trivial extension of manifold neural ODEs that exploits the Lie group structure.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12385718 | PMC |
| http://dx.doi.org/10.3390/e27080878 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Geometric Neural Ordinary Differential Equations: From Manifolds to Lie Groups.
Entropy (Basel)
August 2025
Robotics and Mechatronics, EEMCS, University of Twente (UT), Drienerlolaan 5, 7522 NB Enschede, The Netherlands.
Neural ordinary differential equations (neural ODEs) are a well-established tool for optimizing the parameters of dynamical systems, with applications in image classification, optimal control, and physics learning. Although dynamical systems of interest often evolve on Lie groups and more general differentiable manifolds, theoretical results for neural ODEs are frequently phrased on Rn. We collect recent results for neural ODEs on manifolds and present a unifying derivation of various results that serves as a tutorial to extend existing methods to differentiable manifolds.
View Article and Find Full Text PDFGraph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks.
KDD
August 2025
Emory University, Atlanta, GA, USA.
Graph Neural Networks (GNNs) and differential equations (DEs) are two rapidly advancing areas of research that have shown remarkable synergy in recent years. GNNs have emerged as powerful tools for learning on graph-structured data, while differential equations provide a principled framework for modeling continuous dynamics across time and space. The intersection of these fields has led to innovative approaches that leverage the strengths of both, enabling applications in physics-informed learning, spatiotemporal modeling, and scientific computing.
View Article and Find Full Text PDFIdentification of the governing equation of stimulus-response data for run-and-tumble dynamics.
PLoS Comput Biol
August 2025
School of Mathematics, Shanghai Jiao Tong University, Shanghai, China.
The run-and-tumble behavior is a simple yet powerful mechanism that enables microorganisms to efficiently navigate and adapt to their environment. These organisms run and tumble alternately, with transition rates modulated by intracellular chemical concentration. We introduce a neural network-based model capable of identifying the governing equations underlying run-and-tumble dynamics.
View Article and Find Full Text PDFAn intelligent framework for modeling nonlinear irreversible biochemical reactions using artificial neural networks.
Sci Rep
August 2025
Engineered Biomaterials Research Center, Khazar University, Baku, Azerbaijan.
This paper presents an intelligent computational framework for modeling nonlinear irreversible biochemical reactions (NIBR) using artificial neural networks (ANNs). The biochemical reactions are modeled using an extended Michaelis-Menten kinetic scheme involving enzyme-substrate and enzyme-product complexes, expressed through a system of nonlinear ordinary differential equations (ODEs). Datasets were generated using the Runge-Kutta 4th order (RK4) method and used to train a multilayer feedforward ANN employing the Backpropagation Levenberg-Marquardt (BLM) algorithm.
View Article and Find Full Text PDFChemKANs for combustion chemistry modeling and acceleration.
Phys Chem Chem Phys
August 2025
Department of Mechanical Engineering, Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, MA 02139, USA.
Efficient chemical kinetic model inference and application in combustion are challenging due to large ODE systems and widely separated time scales. Machine learning techniques have been proposed to streamline these models, though strong nonlinearity and numerical stiffness combined with noisy data sources make their application challenging. Here, we introduce ChemKANs, a novel neural network framework with applications both in model inference and simulation acceleration for combustion chemistry.
View Article and Find Full Text PDF