Pages that link to "Item:Q2117336"
From MaRDI portal
The following pages link to Approximation spaces of deep neural networks (Q2117336):
Displaying 48 items.
- Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018 (Q1731982) (← links)
- Provable approximation properties for deep neural networks (Q1742817) (← links)
- A new initialization method based on normed statistical spaces in deep networks (Q2028932) (← links)
- Theory of deep convolutional neural networks. II: Spherical analysis (Q2057723) (← links)
- Constructive deep ReLU neural network approximation (Q2067309) (← links)
- Understanding neural networks with reproducing kernel Banach spaces (Q2105111) (← links)
- Mathematical analysis of finite parameter deep neural network models with skip connections from the viewpoint of representation sets (Q2107473) (← links)
- Nonlinear approximation and (deep) ReLU networks (Q2117331) (← links)
- The Barron space and the flow-induced function spaces for neural network models (Q2117337) (← links)
- Learning with tree tensor networks: complexity estimates and model selection (Q2137001) (← links)
- Approximation properties of deep ReLU CNNs (Q2157922) (← links)
- Designing rotationally invariant neural networks from PDEs and variational methods (Q2168880) (← links)
- Training thinner and deeper neural networks: jumpstart regularization (Q2170213) (← links)
- Universal approximation with quadratic deep networks (Q2185719) (← links)
- Almost everywhere approximation capabilities of double Mellin approximate identity neural networks (Q2403275) (← links)
- The universal approximation theorem for complex-valued neural networks (Q2689134) (← links)
- Approximation properties of residual neural networks for Kolmogorov PDEs (Q2697245) (← links)
- Sobolev-type embeddings for neural network approximation spaces (Q2700875) (← links)
- Deep vs. shallow networks: an approximation theory perspective (Q2835988) (← links)
- Deep Neural Network Approximation Theory (Q5001568) (← links)
- Full error analysis for the training of deep neural networks (Q5083408) (← links)
- State-Space Representations of Deep Neural Networks (Q5154125) (← links)
- A New Function Space from Barron Class and Application to Neural Network Approximation (Q5878925) (← links)
- Neural network approximation (Q5887830) (← links)
- Simultaneous neural network approximation for smooth functions (Q6052416) (← links)
- Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs (Q6062166) (← links)
- Deep learning methods for partial differential equations and related parameter identification problems (Q6070739) (← links)
- Approximation theory of tree tensor networks: tensorized univariate functions (Q6076973) (← links)
- Mesh-informed neural networks for operator learning in finite element spaces (Q6077303) (← links)
- On decision regions of narrow deep neural networks (Q6078750) (← links)
- Deep ReLU neural networks in high-dimensional approximation (Q6079085) (← links)
- Towards Lower Bounds on the Depth of ReLU Neural Networks (Q6100606) (← links)
- Universal regular conditional distributions via probabilistic transformers (Q6101232) (← links)
- Deep Learning in High Dimension: Neural Network Expression Rates for Analytic Functions in \(\pmb{L^2(\mathbb{R}^d,\gamma_d)}\) (Q6109160) (← links)
- Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on Hölder Class (Q6137593) (← links)
- A multivariate Riesz basis of ReLU neural networks (Q6144893) (← links)
- Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs (Q6148127) (← links)
- Learning ability of interpolating deep convolutional neural networks (Q6185680) (← links)
- Two-layer networks with the \(\text{ReLU}^k\) activation function: Barron spaces and derivative approximation (Q6191372) (← links)
- Approximation in shift-invariant spaces with deep ReLU neural networks (Q6341347) (← links)
- Approximation of classifiers by deep perceptron networks (Q6488832) (← links)
- Neural networks with ReLU powers need less depth (Q6535869) (← links)
- Piecewise integrable neural network: an interpretable chaos identification framework (Q6572660) (← links)
- Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces (Q6592113) (← links)
- On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fields (Q6624464) (← links)
- Approximation results for gradient flow trained shallow neural networks in \(1d\) (Q6648717) (← links)
- Sampling complexity of deep approximation spaces (Q6649919) (← links)
- Weighted variation spaces and approximation by shallow ReLU networks (Q6652573) (← links)
