Results 121 to 130 of about 1,345 (197)

Automatic network structure discovery of physics informed neural networks via knowledge distillation. [PDF]

Nat Commun
Liu Z, Liu Y, Yan X, Liu W, Nie H, Guo S, Zhang CA.   +6 more
europepmc   +1 more source

Partial differential equations in data science. [PDF]

Philos Trans A Math Phys Eng Sci
Bertozzi AL, Drenska N, Latz J, Thorpe M.   +3 more
europepmc   +1 more source

WF-PINNs: solving forward and inverse problems of burgers equation with steep gradients using weak-form physics-informed neural networks. [PDF]

Sci Rep
Wang X, Yi S, Gu H, Xu J, Xu W.
europepmc   +1 more source

Adaptive regularization and discretization for nonlinear inverse problems with PDEs

, 2014
In this thesis, efficient methods for the solution of inverse problems, combining adaptive regularization and discretization are proposed. For the computation of a Tikhonov regularization parameter, we consider an inexact Newton method based on Morozov's discrepancy principle. In each step, a regularized problem is solved on a different discretization
openaire   +1 more source

Smoothness and stability in the Alt-Phillips problem. [PDF]

Math Ann
Carducci M, Tortone G.
europepmc   +1 more source

A primer on variational inference for physics-informed deep generative modelling. [PDF]

Philos Trans A Math Phys Eng Sci
Glyn-Davies A, Vadeboncoeur A, Akyildiz OD, Kazlauskaite I, Girolami M.   +4 more
europepmc   +1 more source

Physics-Informed Neural Networks with Unknown Partial Differential Equations: An Application in Multivariate Time Series. [PDF]

Entropy (Basel)
Mortezanejad SAF, Wang R, Mohammad-Djafari A.   +2 more
europepmc   +1 more source

Inf-sup stable space-time Local Discontinuous Galerkin method for the heat equation. [PDF]

J Sci Comput
Gómez S, Perinati C, Stocker P.
europepmc   +1 more source

Information-distilled physics informed deep learning for high order differential inverse problems with extreme discontinuities. [PDF]

Commun Eng
Peng M, Tang H.
europepmc   +1 more source

Gradient-Driven Physics Informed Neural Networks for Conduction Heat Transfer and Incompressible Laminar Flow. [PDF]

J Comput Nonlinear Dyn
Lu T, Shahadat MRB, Liu Q, He R, Jiang X, Li Z.   +5 more
europepmc   +1 more source