English
Related papers

Related papers: Deep Energy-Based Modeling of Discrete-Time Physic…

200 papers

We investigate the parameterization of deep neural networks that by design satisfy the continuity equation, a fundamental conservation law. This is enabled by the observation that any solution of the continuity equation can be represented…

Machine Learning · Computer Science 2022-12-13 Jack Richter-Powell , Yaron Lipman , Ricky T. Q. Chen

Partial Differential Equations (PDE) are fundamental to model different phenomena in science and engineering mathematically. Solving them is a crucial step towards a precise knowledge of the behaviour of natural and engineered systems. In…

This paper proposes the Nerual Energy Descent (NED) via neural network evolution equations for a wide class of deep learning problems. We show that deep learning can be reformulated as the evolution of network parameters in an evolution…

Numerical Analysis · Mathematics 2023-02-22 Wenrui Hao , Chunmei Wang , Xingjian Xu , Haizhao Yang

We introduce a new strategy designed to help physicists discover hidden laws governing dynamical systems. We propose to use machine learning automatic differentiation libraries to develop hybrid numerical models that combine components…

Machine Learning · Computer Science 2019-11-21 Redouane Lguensat , Julien Le Sommer , Sammy Metref , Emmanuel Cosme , Ronan Fablet

Modeling the traffic dynamics is essential for understanding and predicting the traffic spatiotemporal evolution. However, deriving the partial differential equation (PDE) models that capture these dynamics is challenging due to their…

Systems and Control · Electrical Eng. & Systems 2025-05-05 Zihang Wei , Yunlong Zhang , Chenxi Liu , Yang Zhou

As deep learning becomes more prevalent for prediction and control of real physical systems, it is important that these overparameterized models are consistent with physically plausible dynamics. This elicits a problem with how much…

Machine Learning · Computer Science 2021-06-08 Aaron Havens , Girish Chowdhary

Physics-based simulations typically operate with a combination of complex differentiable equations and many scientific and geometric inputs. Our work involves gathering data from those simulations and seeing how well tree-based machine…

Machine Learning · Computer Science 2022-07-29 David Noever , Samuel Hyams

We present a new hybrid physics-based machine-learning approach to reservoir modeling. The methodology relies on a series of deep adversarial neural network architecture with physics-based regularization. The network is used to simulate the…

Machine Learning · Statistics 2020-01-16 Cedric G. Fraces , Adrien Papaioannou , Hamdi Tchelepi

The fundamental laws of physics are intrinsically geometric, dictating the evolution of systems through principles of symmetry and conservation. While modern machine learning offers powerful tools for modeling complex dynamics from data,…

Machine Learning · Computer Science 2025-07-22 Amine Mohamed Aboussalah , Abdessalam Ed-dib

In this paper, we present a systematic framework to derive a Lagrangian scheme for porous medium type generalized diffusion equations by employing a discrete energetic variational approach. Such discrete energetic variational approaches are…

Numerical Analysis · Mathematics 2020-07-15 Chun Liu , Yiwei Wang

Discrete latent space models have recently achieved performance on par with their continuous counterparts in deep variational inference. While they still face various implementation challenges, these models offer the opportunity for a…

Machine Learning · Statistics 2023-08-22 Max Cohen , Maurice Charbit , Sylvain Le Corff

Effective inclusion of physics-based knowledge into deep neural network models of dynamical systems can greatly improve data efficiency and generalization. Such a-priori knowledge might arise from physical principles (e.g., conservation…

Machine Learning · Computer Science 2022-12-13 Franck Djeumou , Cyrus Neary , Eric Goubault , Sylvie Putot , Ufuk Topcu

In this article, a numerical analysis of the asymptotic behavior of the discrete energy associated to a dissipative coupled wave system is conducted. The numerical approximation of the system is constructed using the P1 finite element…

Numerical Analysis · Mathematics 2025-08-22 Toni Sayah , Toufic El Arwadi

Many processes in science and engineering can be described by partial differential equations (PDEs). Traditionally, PDEs are derived by considering first principles of physics to derive the relations between the involved physical quantities…

Machine Learning · Statistics 2019-03-27 Jens Berg , Kaj Nyström

The abundance of data affords researchers to pursue more powerful computational tools to learn the dynamics of complex system, such as neural networks, engineered systems and social networks. Traditional machine learning approaches capture…

Machine Learning · Computer Science 2024-05-16 Yan Shen , Fan Yang , Mingchen Gao , Wen Dong

Physics-Informed Neural Networks (PINNs) have enabled significant improvements in modelling physical processes described by partial differential equations (PDEs). PINNs are based on simple architectures, and learn the behavior of complex…

The great learning ability of deep learning models facilitates us to comprehend the real physical world, making learning to simulate complicated particle systems a promising endeavour. However, the complex laws of the physical world pose…

Machine Learning · Computer Science 2025-08-26 Guangsi Shi , Daokun Zhang , Ming Jin , Shirui Pan , Philip S. Yu

In chemical reaction network theory, ordinary differential equations are used to model the temporal change of chemical species concentration. As the functional form of these ordinary differential equations systems is derived from an…

Molecular Networks · Quantitative Biology 2025-02-27 Anna C. M. Thöni , William E. Robinson , Yoram Bachrach , Wilhelm T. S. Huck , Tal Kachman

Deep operator network (DeepONet) has shown significant promise as surrogate models for systems governed by partial differential equations (PDEs), enabling accurate mappings between infinite-dimensional function spaces. However, when applied…

Machine Learning · Computer Science 2025-10-29 Sharmila Karumuri , Lori Graham-Brady , Somdatta Goswami

A class of A.L.E. time discretisations which inherit key energetic properties (nonlinear dissipation in the absence of forcing and long-term stability under conditions of time dependent loading), irrespective of the time increment employed,…

Fluid Dynamics · Physics 2015-06-26 S. J. Childs