Limitations of the approximation capabilities of neural networks with one hidden layer
From MaRDI portal
Publication:1923890
DOI10.1007/BF02124745zbMath0855.41026MaRDI QIDQ1923890
Xin Li, Charles K. Chui, Hrushikesh N. Mhaskar
Publication date: 13 October 1996
Published in: Advances in Computational Mathematics (Search for Journal in Brave)
Circuits, networks (94C99) Multidimensional problems (41A63) Approximation by other special function classes (41A30)
Related Items (20)
Deep distributed convolutional neural networks: Universality ⋮ Theoretical issues in deep networks ⋮ On the approximation by single hidden layer feedforward neural networks with fixed weights ⋮ Theory of deep convolutional neural networks: downsampling ⋮ A deep network construction that adapts to intrinsic dimensionality beyond the domain ⋮ Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation ⋮ Function approximation by deep networks ⋮ Learning sparse and smooth functions by deep sigmoid nets ⋮ Approximation of nonlinear functionals using deep ReLU networks ⋮ Deep nonparametric regression on approximate manifolds: nonasymptotic error bounds with polynomial prefactors ⋮ Application of radial basis function and generalized regression neural networks in nonlinear utility function specification for travel mode choice modelling ⋮ Complexity of neural network approximation with limited information: A worst case approach ⋮ Limitations of shallow nets approximation ⋮ Universality of deep convolutional neural networks ⋮ Theory of deep convolutional neural networks. II: Spherical analysis ⋮ Deep vs. shallow networks: An approximation theory perspective ⋮ On simultaneous approximations by radial basis function neural networks ⋮ Approximative compactness of linear combinations of characteristic functions ⋮ Extension of localised approximation by neural networks ⋮ Constructive approximate interpolation by neural networks
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Approximation by superposition of sigmoidal and radial basis functions
- Optimal nonlinear approximation
- Approximation properties of a multilayered feedforward artificial neural network
- Degree of approximation by neural and translation networks with a single hidden layer
- Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
- Universal approximation bounds for superpositions of a sigmoidal function
- Neural Networks for Localized Approximation
- Dimension-independent bounds on the degree of approximation by neural networks
- Approximation by superpositions of a sigmoidal function
This page was built for publication: Limitations of the approximation capabilities of neural networks with one hidden layer
