Pages that link to "Item:Q5162358"

The following pages link to Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks (Q5162358):

Displaying 26 items.

• A non-gradient method for solving elliptic partial differential equations with deep neural networks (Q2099748) (← links)
• A deep domain decomposition method based on Fourier features (Q2112697) (← links)
• An efficient neural network method with plane wave activation functions for solving Helmholtz equation (Q2122592) (← links)
• When and why PINNs fail to train: a neural tangent kernel perspective (Q2136450) (← links)
• Improved architectures and training algorithms for deep operator networks (Q2149522) (← links)
• Scientific machine learning through physics-informed neural networks: where we are and what's next (Q2162315) (← links)
• A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems (Q2222703) (← links)
• Multi-scale fusion network: a new deep learning structure for elliptic interface problems (Q2691986) (← links)
• High Order Deep Neural Network for Solving High Frequency Partial Differential Equations (Q5065177) (← links)
• A Consensus-Based Global Optimization Method with Adaptive Momentum Estimation (Q5077702) (← links)
• MOD-Net: A Machine Learning Approach via Model-Operator-Data Network for Solving PDEs (Q5106291) (← links)
• Linearized Learning with Multiscale Deep Neural Networks for Stationary Navier-Stokes Equations with Oscillatory Solutions (Q6069455) (← links)
• VC-PINN: variable coefficient physics-informed neural network for forward and inverse problems of PDEs with variable coefficient (Q6069931) (← links)
• SONets: sub-operator learning enhanced neural networks for solving parametric partial differential equations (Q6087965) (← links)
• Learning high frequency data via the coupled frequency predictor-corrector triangular DNN (Q6104304) (← links)
• A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations (Q6110111) (← links)
• A conservative hybrid deep learning method for Maxwell-Ampère-Nernst-Planck equations (Q6126572) (← links)
• Learning Specialized Activation Functions for Physics-Informed Neural Networks (Q6143615) (← links)
• Physics-informed neural network frameworks for crack simulation based on minimized peridynamic potential energy (Q6153887) (← links)
• Asymptotic-preserving neural networks for multiscale time-dependent linear transport equations (Q6158979) (← links)
• Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs (Q6162913) (← links)
• Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations (Q6171723) (← links)
• A Neural Network Approach for Homogenization of Multiscale Problems (Q6178099) (← links)
• On the spectral bias of coupled frequency predictor-corrector triangular DNN: the convergence analysis (Q6179933) (← links)
• High Order Deep Domain Decomposition Method for Solving High Frequency Interface Problems (Q6188658) (← links)
• Physical informed neural networks with soft and hard boundary constraints for solving advection-diffusion equations using Fourier expansions (Q6202605) (← links)