Expressivity of Deep Neural Networks
From MaRDI portal
Recommendations
- Error bounds for approximations with deep ReLU networks
- Universality of deep convolutional neural networks
- Nonlinear approximation and (deep) ReLU networks
- Multilayer feedforward networks are universal approximators
- Optimal approximation with sparsely connected deep neural networks
- Approximating smooth functions by deep neural networks with sigmoid activation function
- Negative results for approximation using single layer and multilayer feedforward neural networks
- Complexity of shallow networks representing finite mappings
- The capacity of feedforward neural networks
- Function approximation by deep networks
Cited in
(24)- Limitations of shallow nets approximation
- On the relative expressiveness of Bayesian and neural networks
- Deep vs. shallow networks: an approximation theory perspective
- On the expressive power of deep architectures
- Deep distributed convolutional neural networks: universality
- Optimal approximation with sparsely connected deep neural networks
- Deep neural networks, generic universal interpolation, and controlled ODEs
- Nonlinear weighted directed acyclic graph and a priori estimates for neural networks
- Deep neural networks for rotation-invariance approximation and learning
- Neural network approximation
- Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits
- On the capacity of deep generative networks for approximating distributions
- Neural Network Approximation of Coarse-Scale Surrogates in Numerical Homogenization
- Deep dynamic modeling with just two time points: Can we still allow for individual trajectories?
- Lu decomposition and Toeplitz decomposition of a neural network
- Tucker network: expressive power and comparison
- Expressive power of ReLU and step networks under floating-point operations
- Neural network expression rates and applications of the deep parametric PDE method in counterparty credit risk
- Deep neural network expressivity for optimal stopping problems
- Proof of the theory-to-practice gap in deep learning via sampling complexity bounds for neural network approximation spaces
- Approximation results for gradient flow trained shallow neural networks in \(1d\)
- Navigation through non-compact symmetric spaces: a mathematical perspective on Cartan neural networks
- Non-convergence to global minimizers for Adam and stochastic gradient descent optimization and constructions of local minimizers in the training of artificial neural networks
- Combining physics-based and data-driven models: advancing the frontiers of research with scientific machine learning
This page was built for publication: Expressivity of Deep Neural Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5879776)
