Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
From MaRDI portal
Recommendations
- Harmonic analysis of neural networks
- A neural network model structure study based on Fourier
- Artificial Intelligence and Soft Computing - ICAISC 2004
- Neural networks for sinusoidal frequency estimation
- A phase shift deep neural network for high frequency approximation and wave problems
- Determining the Weights of A Fourier Series Neural Network on the Basis of the Multidimensional Discrete Fourier Transform
- Wavelets in the deep learning era
- scientific article; zbMATH DE number 4162242
Cites work
- A Multiscale Neural Network Based on Hierarchical Matrices
- A phase shift deep neural network for high frequency approximation and wave problems
- A priori estimates of the population risk for two-layer neural networks
- An efficient multigrid strategy for large-scale molecular mechanics optimization
- Convergence Estimates for Multigrid Algorithms without Regularity Assumptions
- Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep Potential: A General Representation of a Many-Body Potential Energy Surface
- scientific article; zbMATH DE number 3983811 (Why is no real title available?)
- scientific article; zbMATH DE number 5681750 (Why is no real title available?)
- Machine learning from a continuous viewpoint. I
- Model reduction with memory and the machine learning of dynamical systems
- ReLU deep neural networks and linear finite elements
- SwitchNet: a neural Network Model for forward and inverse scattering problems
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- The implicit bias of gradient descent on separable data
- Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
Cited in
(86)- A non-gradient method for solving elliptic partial differential equations with deep neural networks
- A deep domain decomposition method based on Fourier features
- An efficient neural network method with plane wave activation functions for solving Helmholtz equation
- When and why PINNs fail to train: a neural tangent kernel perspective
- Improved architectures and training algorithms for deep operator networks
- Scientific machine learning through physics-informed neural networks: where we are and what's next
- A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems
- Exploring the common principal subspace of deep features in neural networks
- Multi-scale fusion network: a new deep learning structure for elliptic interface problems
- Adaptive estimation of nonparametric functionals
- On the Exact Computation of Linear Frequency Principle Dynamics and Its Generalization
- High Order Deep Neural Network for Solving High Frequency Partial Differential Equations
- A consensus-based global optimization method with adaptive momentum estimation
- MOD-Net: a machine learning approach via model-operator-data network for solving PDEs
- Linearized Learning with Multiscale Deep Neural Networks for Stationary Navier-Stokes Equations with Oscillatory Solutions
- VC-PINN: variable coefficient physics-informed neural network for forward and inverse problems of PDEs with variable coefficient
- SONets: sub-operator learning enhanced neural networks for solving parametric partial differential equations
- Learning high frequency data via the coupled frequency predictor-corrector triangular DNN
- A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations
- A conservative hybrid deep learning method for Maxwell-Ampère-Nernst-Planck equations
- Learning Specialized Activation Functions for Physics-Informed Neural Networks
- Physics-informed neural network frameworks for crack simulation based on minimized peridynamic potential energy
- Asymptotic-preserving neural networks for multiscale time-dependent linear transport equations
- Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs
- Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
- A Neural Network Approach for Homogenization of Multiscale Problems
- On the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysis
- High Order Deep Domain Decomposition Method for Solving High Frequency Interface Problems
- Physical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansions
- Optimization of random feature method in the high-precision regime
- A causality-DeepONet for causal responses of linear dynamical systems
- Multilevel domain decomposition-based architectures for physics-informed neural networks
- Current density impedance imaging with PINNs
- Interpretable physics-encoded finite element network to handle concentration features and multi-material heterogeneity in hyperelasticity
- A novel recurrent neural network of gated unit based on Euler's method and application
- A block-coordinate approach of multi-level optimization with an application to physics-informed neural networks
- Machine learning algorithm for the Monge-Ampère equation with transport boundary conditions
- AsPINN: Adaptive symmetry-recomposition physics-informed neural networks
- MHDnet: physics-preserving learning for solving magnetohydrodynamics problems
- Loss jump during loss switch in solving PDEs with neural networks
- A hybrid iterative method based on MIONet for PDEs: theory and numerical examples
- MscaleFNO: multi-scale Fourier neural operator learning for oscillatory functions and wave scattering problems
- Deep collocation method: a framework for solving PDEs using neural networks with error control
- Finite expression method for solving high-dimensional partial differential equations
- Why shallow networks struggle to approximate and learn high frequencies
- Momentum-accelerated Richardson(m) neural solvers and their multi-level extensions
- Solving multiscale dynamical systems by deep learning
- Two-scale neural networks for partial differential equations with small parameters
- Embedding principle in depth for the loss landscape analysis of deep neural networks
- Implicit bias in understanding deep learning for solving PDEs beyond Ritz-Galerkin method
- Learnable activation functions in physics-informed neural networks for solving partial differential equations
- A hybrid iterative neural solver based on spectral analysis for parametric PDEs
- Theory of the frequency principle for general deep neural networks
- A Kolmogorov high order deep neural network for high frequency partial differential equations in high dimensions
- Understanding the initial condensation of convolutional neural networks
- A hybrid iterative method for elliptic variational inequalities of the second kind
- Overview frequency principle/spectral bias in deep learning
- Embedding principle: a hierarchical structure of loss landscape of deep neural networks
- Solving partial differential equations based on preconditioning-pretraining physics-informed neural network
- On understanding and overcoming spectral biases of deep neural network learning methods for solving PDEs
- Deep learning-based computational method for soft matter dynamics: deep Onsager-Machlup method
- Constructing probing functions for direct sampling methods for inverse scattering problems with limited-aperture data: finite space framework and deep probing network
- Newton's method and its hybrid with machine learning for Navier-Stokes Darcy models discretized by mixed element methods
- On spectral bias reduction of multi-scale neural networks for regression problems
- Deep learning without global optimization by random Fourier neural networks
- Input gradient annealing neural network for solving Fokker-Planck equations with low temperature
- Heterogeneous peridynamic neural operators: discover biotissue constitutive law and microstructure from digital image correlation measurements
- Physics-informed multiresolution wavelet neural network method for solving partial differential equations
- More consistent accuracy PINN via alternating easy-hard training
- Deep learning for the semi-classical limit of the Schrödinger equation
- Perturbative-NeuSA: A Structured Spectral Framework for Time-Dependent PDEs
- Comparison of a Parametric Physics-Informed Neural Network and a Tensorial Reduced-Order Model for the Shallow-Water Dam-Break Problem
- Evo-GTransNet for Parabolic PDEs: A Fixed-Feature Galerkin Method of Lines with Quadrature-Mass Orthonormalization
- A morphology-adaptive random feature method for inverse source problem of the Helmholtz equation
- A piecewise Fourier-feature-based neural network for elliptic and parabolic interface problems on curved surfaces
- Multiscale finite expression method for PDEs with oscillatory solutions on complex domains
- Physics-informed machine learning in petroleum engineering: advances, applications, and future directions
- On residual minimization for PDEs: failure of PINN, modified equation, and implicit bias
- Casual attention: adaptive enforcement of causality in physics-informed neural networks
- Anchor function: a type of benchmark functions for studying language models
- Finite expression method with TranNet-based function learning for high-dimensional partial differential equations
- Multi-scale Fourier PINNs for fractal nonlinear oscillators and MEMS fractal pull-in
- NEXT: Physics-Informed Neuro-Spectral Exponential Time Differencing Architectures
- Why diffusion models do not memorize: the role of implicit dynamical regularization in training
- The adaptive solution of high-frequency Helmholtz equations via multi-grade deep learning
- CAFE+FNO: Fourier Kernel Generation via Multiplicative Feature Composition
This page was built for publication: Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5162358)
