English
Related papers

Related papers: Structure-preserving neural networks

200 papers

Concise, accurate descriptions of physical systems through their conserved quantities abound in the natural sciences. In data science, however, current research often focuses on regression problems, without routinely incorporating…

Computational Physics · Physics 2020-02-05 Tom Bertalan , Felix Dietrich , Igor Mezić , Ioannis G. Kevrekidis

On the one hand, the dissipated heat of a thermodynamic work extraction process upper bounds the non-predictive information, which the associated system encodes about its environment. Thus, emergent information processing capabilities can…

Neurons and Cognition · Quantitative Biology 2020-09-10 Kai Ueltzhöffer

We propose a neural entropy-stable conservative flux form neural network (NESCFN) for learning hyperbolic conservation laws and their associated entropy functions directly from solution trajectories, without requiring any predefined…

Numerical Analysis · Mathematics 2025-07-03 Lizuo Liu , Lu Zhang , Anne Gelb

The metriplectic formalism is useful for describing complete dynamical systems which conserve energy and produce entropy. This creates challenges for model reduction, as the elimination of high-frequency information will generally not…

Numerical Analysis · Mathematics 2022-12-28 Anthony Gruber , Max Gunzburger , Lili Ju , Zhu Wang

When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-informed models assume access to the full system state. This limits their use in partially…

Machine Learning · Computer Science 2026-05-25 Sunniva Meltzer , Sølve Eidnes , Alexander Johannes Stasik

Conservation of energy is at the core of many physical phenomena and dynamical systems. There have been a significant number of works in the past few years aimed at predicting the trajectory of motion of dynamical systems using neural…

Machine Learning · Computer Science 2022-08-05 Yi Heng Lim , Muhammad Firmansyah Kasim

Physics-informed neural network architectures have emerged as a powerful tool for developing flexible PDE solvers which easily assimilate data, but face challenges related to the PDE discretization underpinning them. By instead adapting a…

Numerical Analysis · Mathematics 2020-12-11 Ravi G. Patel , Indu Manickam , Nathaniel A. Trask , Mitchell A. Wood , Myoungkyu Lee , Ignacio Tomas , Eric C. Cyr

Modeling of conservative systems with neural networks is an area of active research. A popular approach is to use Hamiltonian neural networks (HNNs) which rely on the assumptions that a conservative system is described with Hamilton's…

Artificial Intelligence · Computer Science 2024-07-18 Katsiaryna Haitsiukevich , Alexander Ilin

In recent years, nonlinear dynamic system identification using artificial neural networks has garnered attention due to its broad potential applications across science and engineering. However, purely data-driven approaches often struggle…

Machine Learning · Computer Science 2025-11-06 Fabian J. Roth , Dominik K. Klein , Maximilian Kannapinn , Jan Peters , Oliver Weeger

Recently, there has been growing interest in using physics-informed neural networks (PINNs) to solve differential equations. However, the preservation of structure, such as energy and stability, in a suitable manner has yet to be…

Machine Learning · Computer Science 2024-01-11 Haoyu Chu , Yuto Miyatake , Wenjun Cui , Shikui Wei , Daisuke Furihata

Accurately learning the temporal behavior of dynamical systems requires models with well-chosen learning biases. Recent innovations embed the Hamiltonian and Lagrangian formalisms into neural networks and demonstrate a significant…

Machine Learning · Computer Science 2021-10-04 Shaan Desai , Marios Mattheakis , David Sondak , Pavlos Protopapas , Stephen Roberts

We present a numerical approach for approximating unknown Hamiltonian systems using observation data. A distinct feature of the proposed method is that it is structure-preserving, in the sense that it enforces conservation of the…

Numerical Analysis · Mathematics 2021-07-13 Kailiang Wu , Tong Qin , Dongbin Xiu

A thermodynamically motivated neural network model is described that self-organizes to transport charge associated with internal and external potentials while in contact with a thermal reservoir. The model integrates techniques for rapid,…

Neurons and Cognition · Quantitative Biology 2020-04-22 Todd Hylton

We reconsider the fundamental problem of coarse-graining infinite-dimensional Hamiltonian dynamics to obtain a macroscopic system which includes dissipative mechanisms. In particular, we study the thermodynamical implications concerning…

Mathematical Physics · Physics 2025-06-06 Alexander Mielke , Mark A. Peletier , Johannes Zimmer

Identifying the dynamics of physical systems requires a machine learning model that can assimilate observational data, but also incorporate the laws of physics. Neural Networks based on physical principles such as the Hamiltonian or…

Machine Learning · Statistics 2021-11-22 Jonas Eichelsdörfer , Sebastian Kaltenbach , Phaedon-Stelios Koutsourelakis

Reduced basis methods are popular for approximately solving large and complex systems of differential equations. However, conventional reduced basis methods do not generally preserve conservation laws and symmetries of the full order model.…

Numerical Analysis · Mathematics 2018-03-20 Babak Maboudi Afkham , Jan S. Hesthaven

In purely non-dissipative systems, Lagrangian and Hamiltonian reduction have proven to be powerful tools for deriving physical models with exact conservation laws. We have discovered a hint that an analogous reduction method exists also for…

Plasma Physics · Physics 2020-08-19 Eero Hirvijoki , Joshua W. Burby

Structure-preserving approaches to dynamics discovery have demonstrated great potential for modeling physical systems due to their use of strong inductive biases, which enforce key features such as conservation laws and dissipative…

Machine Learning · Computer Science 2026-05-05 Cheng Jing , Uvini Balasuriya Mudiyanselage , Woojin Cho , Minju Jo , Anthony Gruber , Kookjin Lee

Gaussian process regression is increasingly applied for learning unknown dynamical systems. In particular, the implicit quantification of the uncertainty of the learned model makes it a promising approach for safety-critical applications.…

Machine Learning · Computer Science 2022-06-29 Jan Brüdigam , Martin Schuck , Alexandre Capone , Stefan Sosnowski , Sandra Hirche

We present a physics-based neural network framework for the discovery of constitutive models in fully coupled thermomechanics. In contrast to classical formulations based on the Helmholtz energy, we adopt the internal energy and a…

Computational Engineering, Finance, and Science · Computer Science 2026-05-25 Hagen Holthusen , Paul Steinmann , Ellen Kuhl