The following pages link to (Q4938227):
Displaying 50 items.
- The recovery of ridge functions on the hypercube suffers from the curse of dimensionality (Q1996887) (← links)
- DGM: a deep learning algorithm for solving partial differential equations (Q2002333) (← links)
- Neural networks-based backward scheme for fully nonlinear PDEs (Q2022970) (← links)
- A selective overview of deep learning (Q2038303) (← links)
- Linearized two-layers neural networks in high dimension (Q2039801) (← links)
- The universal approximation property. Characterization, construction, representation, and existence (Q2043428) (← links)
- Neural network with smooth activation functions and without bottlenecks is almost surely a Morse function (Q2048805) (← links)
- Approximation rates for neural networks with encodable weights in smoothness spaces (Q2055067) (← links)
- On the representation by bivariate ridge functions (Q2058579) (← links)
- Symmetry \& critical points for a model shallow neural network (Q2077613) (← links)
- Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network (Q2082130) (← links)
- The construction and approximation of ReLU neural network operators (Q2086452) (← links)
- Discontinuous neural networks and discontinuity learning (Q2088828) (← links)
- A priori and a posteriori error estimates for the deep Ritz method applied to the Laplace and Stokes problem (Q2095152) (← links)
- On the expressive power of message-passing neural networks as global feature map transformers (Q2103899) (← links)
- Understanding neural networks with reproducing kernel Banach spaces (Q2105111) (← links)
- Recovery of regular ridge functions on the ball (Q2108093) (← links)
- Uniform convergence guarantees for the deep Ritz method for nonlinear problems (Q2110466) (← links)
- Explicitly antisymmetrized neural network layers for variational Monte Carlo simulation (Q2112448) (← links)
- Deep learning architectures for nonlinear operator functions and nonlinear inverse problems (Q2113263) (← links)
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing (Q2117328) (← links)
- Approximation spaces of deep neural networks (Q2117336) (← links)
- Universal approximations of invariant maps by neural networks (Q2117338) (← links)
- Robust and resource-efficient identification of two hidden layer neural networks (Q2117339) (← links)
- Exponential ReLU DNN expression of holomorphic maps in high dimension (Q2117341) (← links)
- Adaptive two-layer ReLU neural network. I: Best least-squares approximation (Q2122629) (← links)
- Interpolation and approximation via momentum ResNets and neural ODEs (Q2124500) (← links)
- Challenges in optimization with complex PDE-systems. Abstracts from the workshop held February 14--20, 2021 (hybrid meeting) (Q2131202) (← links)
- Least-squares ReLU neural network (LSNN) method for linear advection-reaction equation (Q2132582) (← links)
- Self-adaptive deep neural network: numerical approximation to functions and PDEs (Q2133768) (← links)
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder (Q2134764) (← links)
- A mesh-free method using piecewise deep neural network for elliptic interface problems (Q2141617) (← links)
- Deep solution operators for variational inequalities via proximal neural networks (Q2146915) (← links)
- Deep learning for the partially linear Cox model (Q2148978) (← links)
- A decision-making machine learning approach in Hermite spectral approximations of partial differential equations (Q2149019) (← links)
- Multivariate neural network interpolation operators (Q2151614) (← links)
- ReLU deep neural networks from the hierarchical basis perspective (Q2159911) (← links)
- Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling (Q2160481) (← links)
- Scientific machine learning through physics-informed neural networks: where we are and what's next (Q2162315) (← links)
- A generative model for fBm with deep ReLU neural networks (Q2171942) (← links)
- An interval uncertainty analysis method for structural response bounds using feedforward neural network differentiation (Q2174709) (← links)
- On the approximation by single hidden layer feedforward neural networks with fixed weights (Q2179313) (← links)
- Probabilistic lower bounds for approximation by shallow perceptron networks (Q2181058) (← links)
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks (Q2182898) (← links)
- Conservative physics-informed neural networks on discrete domains for conservation laws: applications to forward and inverse problems (Q2184334) (← links)
- Nonparametric regression using deep neural networks with ReLU activation function (Q2215715) (← links)
- A review on deep learning in medical image reconstruction (Q2218098) (← links)
- Data driven governing equations approximation using deep neural networks (Q2222362) (← links)
- A mesh-free method for interface problems using the deep learning approach (Q2222664) (← links)
- A global universality of two-layer neural networks with ReLU activations (Q2236407) (← links)
