Multilayer feedforward networks are universal approximators
Neural Networks
The Gibbs phenomenon for piecewise-linear approximation
American Mathematical Monthly
The Gibbs phenomenon for multiple Fourier integrals
Journal of Approximation Theory
On the Gibbs Phenomenon and Its Resolution
SIAM Review
Universal approximation in p-mean by neural networks
Neural Networks
A corner point Gibbs phenomenon for Fourier series in two dimensions
Journal of Approximation Theory
Constructive approximate interpolation by neural networks
Journal of Computational and Applied Mathematics
Padé-Legendre Interpolants for Gibbs Reconstruction
Journal of Scientific Computing
Gibbs' phenomenon in higher dimensions
Journal of Approximation Theory
De-noising by soft-thresholding
IEEE Transactions on Information Theory
Nonlinear wavelet transforms for image coding via lifting
IEEE Transactions on Image Processing
Neural-network approximation of piecewise continuous functions: application to friction compensation
IEEE Transactions on Neural Networks
Edge Detection by Adaptive Splitting
Journal of Scientific Computing
Hi-index | 0.00 |
In this paper, we give a constructive proof that a real, piecewise continuous function can be almost uniformly approximated by single hidden-layer feedforward neural networks (SLFNNs). The construction procedure avoids the Gibbs phenomenon. Computer experiments show that the resulting approximant is much more accurate than SLFNNs trained by gradient descent.