English
Related papers

Related papers: Deep Ritz-Finite Element methods: Neural Network M…

200 papers

Machine learning for scientific applications faces the challenge of limited data. We propose a framework that leverages a priori known physics to reduce overfitting when training on relatively small datasets. A deep neural network is…

Machine Learning · Computer Science 2019-11-22 Jonathan B. Freund , Jonathan F. MacArt , Justin Sirignano

The numerical solution of high dimensional partial differential equations (PDEs) is severely constrained by the curse of dimensionality (CoD), rendering classical grid--based methods impractical beyond a few dimensions. In recent years,…

Numerical Analysis · Mathematics 2026-01-27 Wenzhong Zhang , Zheyuan Hu , Wei Cai , George EM Karniadakis

We use elliptic partial differential equations (PDEs) as examples to show various properties and behaviors when shallow neural networks (SNNs) are used to represent the solutions. In particular, we study the numerical ill-conditioning,…

Numerical Analysis · Mathematics 2025-11-04 Roy Y. He , Ying Liang , Hongkai Zhao , Yimin Zhong

Physics-Informed Neural Networks (PINNs) are mesh-free approaches for the numerical approximation of partial differential equations, where a neural network is trained by minimizing a loss function derived from the governing equations and…

Numerical Analysis · Mathematics 2026-04-03 Medard Govoeyi , Thomas Richter

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact connected by simple curves over which training and test…

Machine Learning · Statistics 2018-10-31 Timur Garipov , Pavel Izmailov , Dmitrii Podoprikhin , Dmitry Vetrov , Andrew Gordon Wilson

In this work, we present a machine learning approach for reducing the error when numerically solving time-dependent partial differential equations (PDE). We use a fully convolutional LSTM network to exploit the spatiotemporal dynamics of…

Machine Learning · Computer Science 2020-02-11 Ben Stevens , Tim Colonius

We present a weak finite element method for elliptic problems in one space dimension. Our analysis shows that this method has more advantages than the known weak Galerkin method proposed for multi-dimensional problems, for example, it has…

Numerical Analysis · Mathematics 2016-06-29 Tie Zhang , Yanli Chen

Physics-informed neural networks solve partial differential equations by training neural networks. Since this method approximates infinite-dimensional PDE solutions with finite collocation points, minimizing discretization errors by…

Machine Learning · Computer Science 2024-12-11 Takashi Matsubara , Takaharu Yaguchi

Physics Informed Neural Networks is a numerical method which uses neural networks to approximate solutions of partial differential equations. It has received a lot of attention and is currently used in numerous physical and engineering…

Numerical Analysis · Mathematics 2025-07-10 Dimitrios Gazoulis , Ioannis Gkanis , Charalambos G. Makridakis

We derive upper bounds on the complexity of ReLU neural networks approximating the solution maps of parametric partial differential equations. In particular, without any knowledge of its concrete shape, we use the inherent…

Numerical Analysis · Mathematics 2020-05-15 Gitta Kutyniok , Philipp Petersen , Mones Raslan , Reinhold Schneider

We investigate the resolution of parabolic PDEs via Extreme Learning Machine (ELMs) Neural Networks, which have a single hidden layer and can be trained at a modest computational cost as compared with Deep Learning Neural Networks. Our…

Numerical Analysis · Mathematics 2022-06-02 Francesco Calabrò , Salvatore Cuomo , Daniela di Serafino , Giuseppe Izzo , Eleonora Messina

In this paper, a shallow Ritz-type neural network for solving elliptic equations with delta function singular sources on an interface is developed. There are three novel features in the present work; namely, (i) the delta function…

Numerical Analysis · Mathematics 2023-06-13 Ming-Chih Lai , Che-Chia Chang , Wei-Syuan Lin , Wei-Fan Hu , Te-Sheng Lin

Conventional finite element methods are known to be tedious in adaptive refinements due to their conformal regularity requirements. Further, the enrichment functions for adaptive refinements are often not readily available in general…

Numerical Analysis · Mathematics 2025-09-11 Jonghyuk Baek , Yanran Wang , J. S. Chen

Extreme learning machine (ELM) is a methodology for solving partial differential equations (PDEs) using a single hidden layer feed-forward neural network. It presets the weight/bias coefficients in the hidden layer with random values, which…

Numerical Analysis · Mathematics 2025-04-30 Chang-Ock Lee , Youngkyu Lee , Byungeun Ryoo

This paper discusses a new method to solve definite integrals using artificial neural networks. The objective is to build a neural network that would be a novel alternative to pre-established numerical methods and with the help of a…

Machine Learning · Computer Science 2019-04-23 Satyasaran Changdar , Snehangshu Bhattacharjee

In this paper, we consider a time-dependent discrete network model with highly varying connectivity. The approximation by time is performed using an implicit scheme. We propose the coarse scale approximation construction of network models…

Numerical Analysis · Mathematics 2024-09-02 Maria Vasilyeva

We develop a finite element method for the Laplace--Beltrami operator on a surface described by a set of patchwise parametrizations. The patches provide a partition of the surface and each patch is the image by a diffeomorphism of a…

Numerical Analysis · Mathematics 2017-08-02 Tobias Jonsson , Mats G. Larson , Karl Larsson

There are many numerical methods for solving partial different equations (PDEs) on manifolds such as classical implicit, finite difference, finite element, and isogeometric analysis methods which aim at improving the interoperability…

Numerical Analysis · Mathematics 2023-11-17 Wenrui Hao , Jonathan D. Hauenstein , Margaret H. Regan , Tingting Tang

The deep energy method (DEM) has been used to solve the elastic deformation of structures with linear elasticity, hyperelasticity, and strain-gradient elasticity material models based on the principle of minimum potential energy. In this…

Computational Engineering, Finance, and Science · Computer Science 2023-01-26 Junyan He , Diab Abueidda , Rashid Abu Al-Rub , Seid Koric , Iwona Jasiuk

Physics informed neural networks (PINNs) are deep learning based techniques for solving partial differential equations (PDEs) encounted in computational science and engineering. Guided by data and physical laws, PINNs find a neural network…

Numerical Analysis · Mathematics 2020-12-30 Yeonjong Shin , Jerome Darbon , George Em Karniadakis