Understanding and mitigating gradient pathologies in physics-informed
neural networks

Understanding and mitigating gradient pathologies in physics-informed neural networks

13 January 2020

Papers citing "Understanding and mitigating gradient pathologies in physics-informed neural networks"

14 / 114 papers shown

Title
Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture S. Niaki E. Haghighat Trevor Campbell Xinglong Li R. Vaziri AI4CE 13 203 0 27 Nov 2020
Accelerating Simulation of Stiff Nonlinear Systems using Continuous-Time Echo State Networks Ranjan Anantharaman Yingbo Ma Shashi Gowda C. Laughman Viral B. Shah Alan Edelman Chris Rackauckas 6 23 0 07 Oct 2020
Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism L. McClenny U. Braga-Neto PINN 28 443 0 07 Sep 2020
When and why PINNs fail to train: A neural tangent kernel perspective Sizhuang He Xinling Yu P. Perdikaris 33 878 0 28 Jul 2020
Physics informed deep learning for computational elastodynamics without labeled data Chengping Rao Hao Sun Yang Liu PINN AI4CE 17 222 0 10 Jun 2020
Bayesian Hidden Physics Models: Uncertainty Quantification for Discovery of Nonlinear Partial Differential Operators from Data Steven Atkinson 6 8 0 07 Jun 2020
Deep learning of free boundary and Stefan problems Sizhuang He P. Perdikaris 27 80 0 04 Jun 2020
DiscretizationNet: A Machine-Learning based solver for Navier-Stokes Equations using Finite Volume Discretization Rishikesh Ranade C. Hill Jay Pathak AI4CE 54 123 0 17 May 2020
Bayesian differential programming for robust systems identification under uncertainty Yibo Yang Mohamed Aziz Bhouri P. Perdikaris OOD 33 32 0 15 Apr 2020
nPINNs: nonlocal Physics-Informed Neural Networks for a parametrized nonlocal universal Laplacian operator. Algorithms and Applications G. Pang M. DÉlia M. Parks George Karniadakis PINN 12 151 0 08 Apr 2020
On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs Yeonjong Shin Jérome Darbon George Karniadakis PINN 9 79 0 03 Apr 2020
hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition E. Kharazmi Zhongqiang Zhang George Karniadakis 128 509 0 11 Mar 2020
Universal Differential Equations for Scientific Machine Learning Christopher Rackauckas Yingbo Ma Julius Martensen Collin Warner K. Zubov R. Supekar Dominic J. Skinner Ali Ramadhan Alan Edelman AI4CE 38 569 0 13 Jan 2020
Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks Ameya Dilip Jagtap Kenji Kawaguchi George Karniadakis ODL 15 85 0 25 Sep 2019