Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks

From MaRDI portal
Publication:5162358

DOI10.4208/cicp.OA-2020-0085OpenAlexW2914483840MaRDI QIDQ5162358

Yanyang Xiao, Tao Luo, Yaoyu Zhang, Zhi-Qin John Xu, Zheng Ma

Publication date: 2 November 2021

Published in: Communications in Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1901.06523




Related Items (28)

An efficient neural network method with plane wave activation functions for solving Helmholtz equationWhen and why PINNs fail to train: a neural tangent kernel perspectiveOn the Exact Computation of Linear Frequency Principle Dynamics and Its GeneralizationImproved architectures and training algorithms for deep operator networksHigh Order Deep Neural Network for Solving High Frequency Partial Differential EquationsScientific machine learning through physics-informed neural networks: where we are and what's nextA Consensus-Based Global Optimization Method with Adaptive Momentum EstimationLinearized Learning with Multiscale Deep Neural Networks for Stationary Navier-Stokes Equations with Oscillatory SolutionsVC-PINN: variable coefficient physics-informed neural network for forward and inverse problems of PDEs with variable coefficientSONets: sub-operator learning enhanced neural networks for solving parametric partial differential equationsMOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEsLearning high frequency data via the coupled frequency predictor-corrector triangular DNNA Hybrid Method for Three-Dimensional Semi-Linear Elliptic EquationsUnnamed ItemA conservative hybrid deep learning method for Maxwell-Ampère-Nernst-Planck equationsLearning Specialized Activation Functions for Physics-Informed Neural NetworksPhysics-informed neural network frameworks for crack simulation based on minimized peridynamic potential energyAsymptotic-preserving neural networks for multiscale time-dependent linear transport equationsSubspace decomposition based DNN algorithm for elliptic type multi-scale PDEsFinite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equationsA Neural Network Approach for Homogenization of Multiscale ProblemsOn the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysisHigh Order Deep Domain Decomposition Method for Solving High Frequency Interface ProblemsPhysical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansionsMulti-scale fusion network: a new deep learning structure for elliptic interface problemsA composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problemsA non-gradient method for solving elliptic partial differential equations with deep neural networksA deep domain decomposition method based on Fourier features


Uses Software


Cites Work


This page was built for publication: Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks