Approximation by Ridge Functions and Neural Networks
From MaRDI portal
Publication:4255766
DOI10.1137/S0036141097322959zbMath0927.41006MaRDI QIDQ4255766
Publication date: 27 June 1999
Published in: SIAM Journal on Mathematical Analysis (Search for Journal in Brave)
Approximation with constraints (41A29) Rate of convergence, degree of approximation (41A25) Spline approximation (41A15)
Related Items (56)
Adaptive two-layer ReLU neural network. I: Best least-squares approximation ⋮ Adaptive two-layer ReLU neural network. II: Ritz approximation to elliptic PDEs ⋮ Neural network approximation ⋮ Continuous and discrete tight frames of orthogonal polynomials for a radially symmetric weight ⋮ On the error of approximation by ridge functions with two fixed directions ⋮ Characterization of an extremal sum of ridge functions ⋮ Local quadrature formulas on the sphere ⋮ Uniform approximation rates and metric entropy of shallow neural networks ⋮ A note on the equioscillation theorem for best ridge function approximation ⋮ Representation of multivariate functions by sums of ridge functions ⋮ A discretized Fourier orthogonal expansion in orthogonal polynomials on a cylinder ⋮ Kähler geometry of framed quiver moduli and machine learning ⋮ Estimation of projection pursuit regression via alternating linearization ⋮ On the representation by linear superpositions ⋮ Radon needlet thresholding ⋮ Error bounds for approximations using multichannel deep convolutional neural networks with downsampling ⋮ Representation of polynomials by linear combinations of radial basis functions ⋮ Approximation of curve-based sleeve functions in high dimensions ⋮ Approximation by sums of ridge functions with fixed directions ⋮ Essential rate for approximation by spherical neural networks ⋮ The plane wave method for inverse problems associated with Helmholtz-type equations ⋮ Numerical integration with polynomial exactness over a spherical cap ⋮ Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions ⋮ Approximation by polynomials and ridge functions of classes of \(s\)-monotone radial functions ⋮ Spherical Marcinkiewicz-Zygmund inequalities and positive quadrature ⋮ Image reconstruction by OPED algorithm with averaging ⋮ Approximation rates for neural networks with general activation functions ⋮ Approximation Properties of Ridge Functions and Extreme Learning Machines ⋮ Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units ⋮ Approximation and learning by greedy algorithms ⋮ Complexity of numerical integration over spherical caps in a Sobolev space setting ⋮ Positive cubature formulas and Marcinkiewicz-Zygmund inequalities on spherical caps ⋮ Weighted quadrature formulas and approximation by zonal function networks on the sphere ⋮ An approximation result for nets in functional estimation ⋮ Cubature over the sphere \(S^{2}\) in Sobolev spaces of arbitrary order ⋮ Error bounds for approximation with neural networks ⋮ Linearized two-layers neural networks in high dimension ⋮ Some problems in the theory of ridge functions ⋮ Limitations of shallow nets approximation ⋮ Linear and nonlinear methods of relief approximation ⋮ Reverse mortgages through artificial intelligence: new opportunities for the actuaries ⋮ On the representation by bivariate ridge functions ⋮ The essential rate of approximation for radial function manifold ⋮ Uniqueness of the Gaussian quadrature for a ball ⋮ OPED reconstruction algorithm for limited angle problem ⋮ Inversion of noisy Radon transform by SVD based needlets ⋮ Ridge wavelets on the ball ⋮ On best approximation by ridge functions ⋮ On the approximation of functional classes equipped with a uniform measure using ridge functions ⋮ The Chebyshev ridge polynomials in 2D tensor tomography ⋮ Optimal lower bounds for cubature error on the sphere \(S^2\) ⋮ Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples ⋮ On best approximation of classes by radial functions ⋮ Robust and resource-efficient identification of two hidden layer neural networks ⋮ High-order approximation rates for shallow neural networks with cosine and \(\mathrm{ReLU}^k\) activation functions ⋮ A New Function Space from Barron Class and Application to Neural Network Approximation
This page was built for publication: Approximation by Ridge Functions and Neural Networks
