English
Related papers

Related papers: Structure-preserving neural networks

200 papers

This paper proposes a data-driven learning framework for identifying governing laws of generalized diffusions with non-gradient components. By combining energy dissipation laws with a physically consistent penalty and first-moment…

Computational Physics · Physics 2025-08-11 Fanze Kong , Chen-Chih Lai , Yubin Lu

Biological systems have to build models from their sensory data that allow them to efficiently process previously unseen inputs. Here, we study a neural network learning a linearly separable rule using examples provided by a teacher. We…

Statistical Mechanics · Physics 2017-11-22 Sebastian Goldt , Udo Seifert

While data-driven methods offer significant promise for modeling complex materials, they often face challenges in generalizing across diverse physical scenarios and maintaining physical consistency. To address these limitations, we propose…

Graphics · Computer Science 2025-10-27 Xueguang Xie , Shu Yan , Shiwen Jia , Siyu Yang , Aimin Hao , Yang Gao , Peng Yu

Many dynamical systems -- from robots interacting with their surroundings to large-scale multiphysics systems -- involve a number of interacting subsystems. Toward the objective of learning composite models of such systems from data, we…

Machine Learning · Computer Science 2023-05-16 Cyrus Neary , Ufuk Topcu

We introduce a machine-learning-based framework for constructing continuum non-Newtonian fluid dynamics model directly from a micro-scale description. Dumbbell polymer solutions are used as examples to demonstrate the essential ideas. To…

Computational Physics · Physics 2020-10-27 Huan Lei , Lei Wu , Weinan E

Biological, artificial, and physical systems dissipate energy to accurately transmit information. While tools of information theory have been used to characterize information-processing capabilities, how reliably this information is…

Statistical Mechanics · Physics 2026-05-29 Giorgio Nicoletti , Daniel M. Busiello

The rapid growth of research in exploiting machine learning to predict chaotic systems has revived a recent interest in Hamiltonian Neural Networks (HNNs) with physical constraints defined by the Hamilton's equations of motion, which…

Machine Learning · Computer Science 2021-06-02 Chen-Di Han , Bryan Glaz , Mulugeta Haile , Ying-Cheng Lai

From physics to engineering, biology and social science, natural and artificial systems are characterized by interconnected topologies whose features - e.g., heterogeneous connectivity, mesoscale organization, hierarchy - affect their…

Physics and Society · Physics 2021-09-01 Marco Grassia , Manlio De Domenico , Giuseppe Mangioni

We numerically show that a deep neural network (DNN) can learn macroscopic thermodynamic laws purely from microscopic data. Using molecular dynamics simulations, we generate the data of snapshot images of gas particles undergoing adiabatic…

Statistical Mechanics · Physics 2025-11-21 Hiroto Kuroyanagi , Tatsuro Yuge

Ensemble weather predictions require statistical post-processing of systematic errors to obtain reliable and accurate probabilistic forecasts. Traditionally, this is accomplished with distributional regression models in which the parameters…

Machine Learning · Statistics 2019-04-01 Stephan Rasp , Sebastian Lerch

Much attention has recently been devoted to data-based computing of evolution of physical systems. In such approaches, information about data points from past trajectories in phase space is used to reconstruct the equations of motion and to…

Machine Learning · Computer Science 2026-03-24 Christopher Eldred , François Gay-Balmaz , Vakhtang Putkaradze

To accurately compute data-based prediction of Hamiltonian systems, especially the long-term evolution of such systems, it is essential to utilize methods that preserve the structure of the equations over time. We consider a case that is…

Machine Learning · Computer Science 2024-08-30 Christopher Eldred , François Gay-Balmaz , Vakhtang Putkaradze

Hamiltonian systems with multiple timescales arise in molecular dynamics, classical mechanics, and theoretical physics. Long-time numerical integration of such systems requires resolving fast dynamics with very small time steps, which…

Numerical Analysis · Mathematics 2025-10-30 Rui Fang , Richard Tsai

Recent advances in the application of physics-informed learning into the field of fluid mechanics have been predominantly grounded in the Newtonian framework, primarly leveraging Navier-Stokes Equation or one of its various derivative to…

Fluid Dynamics · Physics 2024-04-25 Hussam Alhussein , Mohammed Daqaq

Physical dynamical systems can be viewed as natural information processors: their systems preserve, transform, and disperse input information. This perspective motivates learning not only from data generated by such systems, but also how to…

Machine Learning · Computer Science 2026-03-05 Felix Köster , Atsushi Uchida

This paper presents a new method for learning dissipative Hamiltonian dynamics from a limited and noisy dataset. The method uses the Helmholtz decomposition to learn a vector field as the sum of a symplectic and a dissipative vector field.…

Machine Learning · Computer Science 2025-03-18 Torbjørn Smith , Olav Egeland

Predictive statistical mechanics is a form of inference from available data, without additional assumptions, for predicting reproducible phenomena. By applying it to systems with Hamiltonian dynamics, a problem of predicting the macroscopic…

Statistical Mechanics · Physics 2015-09-22 Domagoj Kuic

In this work, we introduce Dissipative SymODEN, a deep learning architecture which can infer the dynamics of a physical system with dissipation from observed state trajectories. To improve prediction accuracy while reducing network size,…

Machine Learning · Computer Science 2020-05-01 Yaofeng Desmond Zhong , Biswadip Dey , Amit Chakraborty

This work is devoted to the study of dissipative fluid systems, through the lens of a geometric variational formulation. Building upon previous works extending Hamilton's principle to non-equilibrium thermodynamics, the present method…

Mathematical Physics · Physics 2026-04-07 Bastien Manach-Pérennou , François Gay-Balmaz

Discovering the underlying behavior of complex systems is an important topic in many science and engineering disciplines. In this paper, we propose a novel neural network framework, finite difference neural networks (FDNet), to learn…

Machine Learning · Statistics 2020-06-04 Zheng Shi , Nur Sila Gulgec , Albert S. Berahas , Shamim N. Pakzad , Martin Takáč
‹ Prev 1 4 5 6 7 8 10 Next ›