Pages that link to "Item:Q5004339"

The following pages link to Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth (Q5004339):

Displaying 17 items.

• Optimal approximation rate of ReLU networks in terms of width and depth (Q2065073) (← links)
• Discontinuous neural networks and discontinuity learning (Q2088828) (← links)
• SelectNet: self-paced learning for high-dimensional partial differential equations (Q2131038) (← links)
• DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method (Q2672762) (← links)
• Active learning based sampling for high-dimensional nonlinear partial differential equations (Q2683063) (← links)
• High Order Deep Neural Network for Solving High Frequency Partial Differential Equations (Q5065177) (← links)
• Simultaneous neural network approximation for smooth functions (Q6052416) (← links)
• Deep Neural Networks for Solving Large Linear Systems Arising from High-Dimensional Problems (Q6054285) (← links)
• Neural network approximation: three hidden layers are enough (Q6054944) (← links)
• Convergence of deep convolutional neural networks (Q6077046) (← links)
• On the recovery of internal source for an elliptic system by neural network approximation (Q6080357) (← links)
• Friedrichs Learning: Weak Solutions of Partial Differential Equations via Deep Learning (Q6108164) (← links)
• Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class (Q6137593) (← links)
• A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology (Q6143617) (← links)
• Designing universal causal deep learning models: The geometric (Hyper)transformer (Q6196301) (← links)
• On mathematical modeling in image reconstruction and beyond (Q6200218) (← links)
• Solving PDEs on unknown manifolds with machine learning (Q6499004) (← links)