A multiscale neural network based on hierarchical matrices

Abstract

In this work we introduce a new multiscale artificial neural network based on the structure of $\mathcal{H}$-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 Schrödinger equations and the Kohn-Sham density functional theory.

arXiv comment26 pages, 11 figures

References in corpus (15)

• Deep Learning in Neural Networks: An Overview
• A Survey on Deep Learning in Medical Image Analysis
• Sequence to Sequence Learning with Neural Networks
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• DGM: A deep learning algorithm for solving partial differential equations
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Understanding deep learning requires rethinking generalization
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Deep Image Prior
• Generalized Multiscale Finite Element Methods (GMsFEM)
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Deep multi-scale video prediction beyond mean square error
• Learning Functions: When Is Deep Better Than Shallow
• Deep Multiscale Model Learning
• Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks

Cited by in corpus (16)

• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
• Physics-Informed Neural Operator for Learning Partial Differential Equations
• Solving Electrical Impedance Tomography with Deep Learning
• Neural Jump Stochastic Differential Equations
• Efficient Deep Learning Techniques for Multiphase Flow Simulation in Heterogeneous Porous Media
• BCR-Net: a neural network based on the nonstandard wavelet form
• Variational training of neural network approximations of solution maps for physical models
• Multi-scale Deep Neural Networks for Solving High Dimensional PDEs
• Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
• Solving Optical Tomography with Deep Learning
• SwitchNet: a neural network model for forward and inverse scattering problems
• Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
• Efficient Long-Range Convolutions for Point Clouds
• Accurate and Robust Deep Learning Framework for Solving Wave-Based Inverse Problems in the Super-Resolution Regime
• A multiscale neural network based on hierarchical nested bases