A Multiscale Neural Network Based on Hierarchical Matrices
From MaRDI portal
\(\mathcal{H}\)-matrixconvolutional neural networklocally connected neural networkmultiscale neural network
NLS equations (nonlinear Schrödinger equations) (35Q55) PDEs in connection with biology, chemistry and other natural sciences (35Q92) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75) Computational density functional analysis in statistical mechanics (82M36) Neural networks for/in biological studies, artificial life and related topics (92B20)
Abstract: In this work we introduce a new multiscale artificial neural network based on the structure of -matrices. This network generalizes the latter to the nonlinear case by introducing a local deep neural network at each spatial scale. Numerical results indicate that the network is able to efficiently approximate discrete nonlinear maps obtained from discretized nonlinear partial differential equations, such as those arising from nonlinear Schr"odinger equations and the Kohn-Sham density functional theory.
Recommendations
- A multiscale neural network based on hierarchical nested bases
- Hierarchically structured neural networks: A way to shape a `magma' of neurons
- ReLU deep neural networks from the hierarchical basis perspective
- A Neural Network Approach for Homogenization of Multiscale Problems
- Hierarchical neural networks for image interpretation.
Cites work
- A fast algorithm for particle simulations
- A multiscale neural network based on hierarchical nested bases
- A sparse \({\mathcal H}\)-matrix arithmetic: General complexity estimates
- A sparse matrix arithmetic based on \({\mathfrak H}\)-matrices. I: Introduction to \({\mathfrak H}\)-matrices
- A wavelet tour of signal processing. The sparse way.
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- An introduction to hierarchical matrices
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Butterfly-net: optimal function representation based on convolutional neural networks
- Computing the Ground State Solution of Bose--Einstein Condensates by a Normalized Gradient Flow
- Convergence analysis of the generalized empirical interpolation method
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep multiscale model learning
- Deep relaxation: partial differential equations for optimizing deep neural networks
- DGM: a deep learning algorithm for solving partial differential equations
- Efficient reduced-basis treatment of nonaffine and nonlinear partial differential equations
- Fast construction of hierarchical matrix representation from matrix-vector multiplication
- Generalized multiscale finite element methods. Nonlinear elliptic equations
- Hidden physics models: machine learning of nonlinear partial differential equations
- Introduction to hierarchical matrices with applications.
- Literature survey on low rank approximation of matrices
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- Multi-Level Adaptive Solutions to Boundary-Value Problems
- Multiscale finite element methods for porous media flows and their applications
- Solving high-dimensional partial differential equations using deep learning
- Solving parametric PDE problems with artificial neural networks
- Spectral Methods in MATLAB
Cited in
(34)- Efficient long-range convolutions for point clouds
- Meta-learning pseudo-differential operators with deep neural networks
- Int-Deep: a deep learning initialized iterative method for nonlinear problems
- 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
- Using neural networks to accelerate the solution of the Boltzmann equation
- MIM: a deep mixed residual method for solving high-order partial differential equations
- BCR-net: A neural network based on the nonstandard wavelet form
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- A multiscale neural network based on hierarchical nested bases
- AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable Basis Expansion for Multiphase Flow Problems
- MOD-Net: a machine learning approach via model-operator-data network for solving PDEs
- A seamless multiscale operator neural network for inferring bubble dynamics
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
- A multi-scale DNN algorithm for nonlinear elliptic equations with multiple scales
- Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
- SwitchNet: a neural Network Model for forward and inverse scattering problems
- Multilevel Artificial Neural Network Training for Spatially Correlated Learning
- Multilevel Fine-Tuning: Closing Generalization Gaps in Approximation of Solution Maps under a Limited Budget for Training Data
- Accuracy and architecture studies of residual neural network method for ordinary differential equations
- A matrix modular neural network based on task decomposition with subspace division by adaptive affinity propagation clustering
- Sparse Recovery of Elliptic Solvers from Matrix-Vector Products
- Optimal Dirichlet boundary control by Fourier neural operators applied to nonlinear optics
- A Reduced Order Schwarz Method for Nonlinear Multiscale Elliptic Equations Based on Two-Layer Neural Networks
- Solving inverse problems with deep learning
- Kernel methods are competitive for operator learning
- Learning-based multi-continuum model for multiscale flow problems
- Fractional weak adversarial networks for the stationary fractional advection dispersion equations
- Theory of the frequency principle for general deep neural networks
- Overview frequency principle/spectral bias in deep learning
- Physics-informed Fourier neural operators: a machine learning method for parametric partial differential equations
- Dilated convolution neural operator for multiscale partial differential equations
- Multiscale neural networks for approximating Green's functions
- Operator learning for hyperbolic PDEs
Describes a project that uses
Uses Software
This page was built for publication: A Multiscale Neural Network Based on Hierarchical Matrices
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5222107)
