A multi-scale DNN algorithm for nonlinear elliptic equations with multiple scales
From MaRDI portal
(Redirected from Publication:5162363)
\(p\)-Laplacian equationactivation functiondeep neural network (DNN)multi-scale elliptic problemvariational formulation
Nonlinear boundary value problems for nonlinear elliptic equations (35J66) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Finite element, Rayleigh-Ritz and Galerkin methods for boundary value problems involving PDEs (65N30) Artificial neural networks and deep learning (68T07)
Abstract: Algorithms based on deep neural networks (DNNs) have attracted increasing attention from the scientific computing community. DNN based algorithms are easy to implement, natural for nonlinear problems, and have shown great potential to overcome the curse of dimensionality. In this work, we utilize the multi-scale DNN-based algorithm (MscaleDNN) proposed by Liu, Cai and Xu (2020) to solve multi-scale elliptic problems with possible nonlinearity, for example, the p-Laplacian problem. We improve the MscaleDNN algorithm by a smooth and localized activation function. Several numerical examples of multi-scale elliptic problems with separable or non-separable scales in low-dimensional and high-dimensional Euclidean spaces are used to demonstrate the effectiveness and accuracy of the MscaleDNN numerical scheme.
Recommendations
- Multi-scale deep neural network (MscaleDNN) for solving Poisson-Boltzmann equation in complex domains
- A Multiscale Neural Network Based on Hierarchical Matrices
- Multi-scale fusion network: a new deep learning structure for elliptic interface problems
- Deep neural network approximation for high-dimensional elliptic PDEs with boundary conditions
- Multi-Scale Deep Neural Network (MscaleDNN) Methods for Oscillatory Stokes Flows in Complex Domains
Cites work
- A hybridizable discontinuous Galerkin method for the p-Laplacian
- A mesh-free method for interface problems using the deep learning approach
- A multiscale model reduction method for nonlinear monotone elliptic equations in heterogeneous media
- Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
- Analysis of the finite element heterogeneous multiscale method for quasilinear elliptic homogenization problems
- Data driven governing equations approximation using deep neural networks
- Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks
- Deep learning
- DGM: a deep learning algorithm for solving partial differential equations
- Error bounds for approximations with deep ReLU networks
- Finite difference methods for the infinity Laplace and \(p\)-Laplace equations
- Finite Element Approximation of the Parabolic p-Laplacian
- Fractional estimates for non-differentiable elliptic systems with general growth
- Heterogeneous multiscale methods: a review
- Homogenization of Parabolic Equations with a Continuum of Space and Time Scales
- scientific article; zbMATH DE number 1375522 (Why is no real title available?)
- scientific article; zbMATH DE number 3596197 (Why is no real title available?)
- scientific article; zbMATH DE number 1350773 (Why is no real title available?)
- scientific article; zbMATH DE number 1392848 (Why is no real title available?)
- Machine learning from a continuous viewpoint. I
- Multiscale Finite Element Methods
- Numerical homogenization of the acoustic wave equations with a continuum of scales
- Optimality of an adaptive finite element method for the p-Laplacian equation
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Polyharmonic homogenization, rough polyharmonic splines and sparse super-localization
- Preconditioned descent algorithms for \(p\)-Laplacian
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- The element-free Galerkin method for the nonlinear \(p\)-Laplacian equation
- The general theory of homogenization. A personalized introduction
- Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
- WEB-spline-based mesh-free finite element approximation for p-Laplacian
Cited in
(28)- A deep domain decomposition method based on Fourier features
- Multi-scale fusion network: a new deep learning structure for elliptic interface problems
- MOD-Net: a machine learning approach via model-operator-data network for solving PDEs
- Multi-scale deep neural network (MscaleDNN) for solving Poisson-Boltzmann equation in complex domains
- Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions
- Solving multiscale elliptic problems by sparse radial basis function neural networks
- Three ways to solve partial differential equations with neural networks — A review
- Learning Specialized Activation Functions for Physics-Informed Neural Networks
- A novel multi-scale loss function for classification problems in machine learning
- Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs
- Adaptive Learning Rate Residual Network Based on Physics-Informed for Solving Partial Differential Equations
- A Reduced Order Schwarz Method for Nonlinear Multiscale Elliptic Equations Based on Two-Layer Neural Networks
- Physical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansions
- Solving a class of multi-scale elliptic PDEs by means of Fourier-based mixed physics informed neural networks
- A block-coordinate approach of multi-level optimization with an application to physics-informed neural networks
- Laplace-fPINNs: Laplace-based fractional physics-informed neural networks for solving forward and inverse problems of a time fractional equation
- Adaptive pseudo-solution-assisted PINNs for multiscale Darcy and Darcy-Forchheimer equations
- Tensor neural network-based machine learning method for elliptic multiscale problems
- Two-scale neural networks for partial differential equations with small parameters
- Implicit bias in understanding deep learning for solving PDEs beyond Ritz-Galerkin method
- Theory of the frequency principle for general deep neural networks
- Overview frequency principle/spectral bias in deep learning
- A generalized physics-driven neural network for micromechanical and microstructural evolution of heterogeneous materials
- On spectral bias reduction of multi-scale neural networks for regression problems
- Dilated convolution neural operator for multiscale partial differential equations
- Deep learning for the semi-classical limit of the Schrödinger equation
- A conformal prediction framework for uncertainty quantification in physics-informed neural networks
- On residual minimization for PDEs: failure of PINN, modified equation, and implicit bias
This page was built for publication: A multi-scale DNN algorithm for nonlinear elliptic equations with multiple scales
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5162363)
