MgNet: a unified framework of multigrid and convolutional neural network
From MaRDI portal
Publication:2316958
DOI10.1007/s11425-019-9547-2zbMath1476.65026arXiv1901.10415OpenAlexW2912389156WikidataQ127799282 ScholiaQ127799282MaRDI QIDQ2316958
Publication date: 7 August 2019
Published in: Science China. Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1901.10415
Multigrid methods; domain decomposition for boundary value problems involving PDEs (65N55) Artificial neural networks and deep learning (68T07) Knowledge representation (68T30) Computational issues in computer and robotic vision (65D19)
Related Items (36)
Translating numerical concepts for PDEs into neural architectures ⋮ PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain ⋮ PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries ⋮ Bayesian sparse learning with preconditioned stochastic gradient MCMC and its applications ⋮ A Helmholtz equation solver using unsupervised learning: application to transcranial ultrasound ⋮ A modified batch intrinsic plasticity method for pre-training the random coefficients of extreme learning machines ⋮ Meta-mgnet: meta multigrid networks for solving parameterized partial differential equations ⋮ Deep solution operators for variational inequalities via proximal neural networks ⋮ Approximation properties of deep ReLU CNNs ⋮ Numerical approximation of partial differential equations by a variable projection method with artificial neural networks ⋮ Probabilistic deep learning for real-time large deformation simulations ⋮ On computing the hyperparameter of extreme learning machines: algorithm and application to computational PDEs, and comparison with classical and high-order finite elements ⋮ DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method ⋮ Solving the discretised neutron diffusion equations using neural networks ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ Accuracy and architecture studies of residual neural network method for ordinary differential equations ⋮ Learning Optimal Multigrid Smoothers via Neural Networks ⋮ MGIC: Multigrid-in-Channels Neural Network Architectures ⋮ Deep learning discrete calculus (DLDC): a family of discrete numerical methods by universal approximation for STEM education to frontier research ⋮ A Novel Deep Neural Network Algorithm for the Helmholtz Scattering Problem In the Unbounded Domain ⋮ A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology ⋮ Connections between numerical algorithms for PDEs and neural networks ⋮ Numerical computation of partial differential equations by hidden-layer concatenated extreme learning machine ⋮ Deep learning and multi-level featurization of graph representations of microstructural data ⋮ Side effects of learning from low-dimensional data embedded in a Euclidean space ⋮ DNN-MG: a hybrid neural network/finite element method with applications to 3D simulations of the Navier-Stokes equations ⋮ On mathematical modeling in image reconstruction and beyond ⋮ A review on deep learning in medical image reconstruction ⋮ Local extreme learning machines and domain decomposition for solving linear and nonlinear partial differential equations ⋮ Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks ⋮ Enforcing Imprecise Constraints on Generative Adversarial Networks for Emulating Physical Systems ⋮ Unnamed Item ⋮ MgNet ⋮ Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network ⋮ Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data ⋮ Multiresolution convolutional autoencoders
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- AlexNet
- Iterative solution of large sparse systems of equations. Transl. from the German
- Multilayer feedforward networks are universal approximators
- Provable approximation properties for deep neural networks
- Exponential convergence of the deep neural network approximation for analytic functions
- A proposal on machine learning via dynamical systems
- Iterative Methods by Space Decomposition and Subspace Correction
- Universal approximation bounds for superpositions of a sigmoidal function
- The method of alternating projections and the method of subspace corrections in Hilbert space
- Deep distributed convolutional neural networks: Universality
- Algebraic multigrid methods
- Optimization Methods for Large-Scale Machine Learning
- Approximation by superpositions of a sigmoidal function
This page was built for publication: MgNet: a unified framework of multigrid and convolutional neural network
