Neural‐Initialized Newton: Accelerating Nonlinear Finite Elements via Operator Learning
ABSTRACT We propose a Newton‐based scheme, initialized by neural operator predictions, to accelerate the parametric solution of nonlinear problems in computational solid mechanics. First, a physics‐informed neural operator based on conditional neural fields or Fourier neural operators is trained to approximate the nonlinear parametric solution of the ...
Kianoosh Taghikhani +5 more
wiley +1 more source
Generative discovery of partial differential equations by learning from math handbooks. [PDF]
Xu H +7 more
europepmc +1 more source
Deterministic, stochastic, and mean-field PDE models in neuroscience. [PDF]
Çetin C +5 more
europepmc +1 more source
Gradient-Driven Physics Informed Neural Networks for Conduction Heat Transfer and Incompressible Laminar Flow. [PDF]
Lu T +5 more
europepmc +1 more source
NeuberNet: a neural operator solving elastic-plastic partial differential equations at V-notches from low-fidelity elastic simulations. [PDF]
Grossi T, Beghini M, Benedetti M.
europepmc +1 more source
A fast, accurate and oscillation-free spectral collocation solver for high-dimensional transport problems. [PDF]
Cavallini N +3 more
europepmc +1 more source
Physics-informed neural network analysis of kerosene-based penta-hybrid nanofluid flow and heat transfer. [PDF]
Makhdoum BM +8 more
europepmc +1 more source
Physics-informed neural networks for physiological signal processing and modeling: a narrative review. [PDF]
Zhao A, Fattahi D, Hu X.
europepmc +1 more source
Active control of flexible spacecraft in orbit based on partial differential equations. [PDF]
Zhang B, Wen M.
europepmc +1 more source
Entropy optimization of magnetohydrodynamic Casson hybrid nanofluid flow over a rotating disk with Cattaneo Christov heat flux. [PDF]
Gubena T, Ibrahim W.
europepmc +1 more source

