Approximation by superposition of sigmoidal and radial basis functions
From MaRDI portal
Publication:1201935
DOI10.1016/0196-8858(92)90016-PzbMath0763.41015MaRDI QIDQ1201935
Charles A. Micchelli, Hrushikesh N. Mhaskar
Publication date: 17 January 1993
Published in: Advances in Applied Mathematics (Search for Journal in Brave)
Related Items
On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights ⋮ Approximation by network operators with logistic activation functions ⋮ Interpolation and rates of convergence for a class of neural networks ⋮ DENSITY RESULTS BY DEEP NEURAL NETWORK OPERATORS WITH INTEGER WEIGHTS ⋮ CONSTRUCTIVE ESTIMATION OF APPROXIMATION FOR TRIGONOMETRIC NEURAL NETWORKS ⋮ Approximation properties of a multilayered feedforward artificial neural network ⋮ On local and global sigma-pi neural networks. A common link ⋮ Lower estimation of approximation rate for neural networks ⋮ Neural networks and seasonality: Some technical considerations ⋮ Network approximation of input-output maps and functionals ⋮ Uniform approximation of discrete-space multidimensional myopic maps ⋮ Solving numerically nonlinear systems of balance laws by multivariate sigmoidal functions approximation ⋮ Approximation to functions of several variables by superpositions of functions of fewer variables ⋮ Neural network with unbounded activation functions is universal approximator ⋮ Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions ⋮ Neural network interpolation operators activated by smooth ramp functions ⋮ Neural networks for optimal approximation of continuous functions in \(\mathbb R^d\) ⋮ Solving Volterra integral equations of the second kind by sigmoidal functions approximation ⋮ Chebyshev approximation by discrete superposition. Application to neural networks ⋮ Networks and closed balls ⋮ Hyperbolic sigma-pi neural network operators for compactly supported continuous functions ⋮ Limitations of the approximation capabilities of neural networks with one hidden layer ⋮ Approximation by neural networks with sigmoidal functions ⋮ On the approximation by single hidden layer feedforward neural networks with fixed weights ⋮ The construction and approximation of some neural network operators ⋮ Best approximation by linear combinations of characteristic functions of half-spaces. ⋮ Kähler geometry of framed quiver moduli and machine learning ⋮ Neural network interpolation operators optimized by Lagrange polynomial ⋮ The role of nonpolynomiality in uniform approximation by RBF networks of Hankel translates ⋮ A survey on universal approximation and its limits in soft computing techniques. ⋮ Universality of neural networks with a sigmoidal activation or discriminatory functions on functional Banach lattices over the real line ⋮ Analysis of convergence performance of neural networks ranking algorithm ⋮ Unnamed Item ⋮ The errors of simultaneous approximation of multivariate functions by neural networks ⋮ The ridge function representation of polynomials and an application to neural networks ⋮ Quasi-interpolation for surface reconstruction from scattered data with radial basis function ⋮ Relaxed conditions for radial-basis function networks to be universal approximators. ⋮ Approximation results for neural network operators activated by sigmoidal functions ⋮ A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function ⋮ Multivariate neural network operators with sigmoidal activation functions ⋮ Minimization of Error Functionals over Perceptron Networks ⋮ A collocation method for solving nonlinear Volterra integro-differential equations of neutral type by sigmoidal functions ⋮ Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions ⋮ Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis ⋮ \(L^p\) approximation capability of RBF neural networks ⋮ Misspecified diffusion models with high-frequency observations and an application to neural networks ⋮ Interpolation by neural network operators activated by ramp functions ⋮ Convergence of a family of neural network operators of the Kantorovich type ⋮ Neural networks for optimal approximation of continuous functions on the unit sphere ⋮ Approximation by series of sigmoidal functions with applications to neural networks ⋮ Constructive methods of approximation by ridge functions and radial functions ⋮ Multivariate sigmoidal neural network approximation ⋮ The approximation operators with sigmoidal functions ⋮ A way of constructing translation network operators by Bernstein operators ⋮ \textit{hp}-VPINNs: variational physics-informed neural networks with domain decomposition ⋮ Neural Networks for Localized Approximation ⋮ New study on neural networks: the essential order of approximation ⋮ The essential order of approximation for nearly exponential type neural networks ⋮ Complexity of Gaussian-radial-basis networks approximating smooth functions ⋮ Some problems in the theory of ridge functions ⋮ Equivalence of approximation by convolutional neural networks and fully-connected networks ⋮ Separation conditions and approximation of discrete-time and discrete-space systems ⋮ Approximation rates for neural networks with encodable weights in smoothness spaces ⋮ A note on error bounds for function approximation using nonlinear networks ⋮ Time-delay neural networks, Volterra series, and rates of approximation ⋮ Quantitative approximation by perturbed Kantorovich-Choquet neural network operators ⋮ Rates of approximation by neural network interpolation operators ⋮ Universal approximation capability of EBF neural networks with arbitrary activation functions ⋮ On simultaneous approximations by radial basis function neural networks ⋮ Simultaneous \(\mathbf L^p\)-approximation order for neural networks ⋮ Approximation by perturbed neural network operators ⋮ Approximations by multivariate perturbed neural network operators ⋮ Wiener's tauberian theorems for the Fourier-Bessel transformation and uniform approximation by RBF networks of Delsarte translates ⋮ Optimal Approximation with Sparsely Connected Deep Neural Networks ⋮ Approximating functions with multi-features by deep convolutional neural networks ⋮ On best approximation of classes by radial functions ⋮ Universal approximations of invariant maps by neural networks ⋮ Exponential ReLU DNN expression of holomorphic maps in high dimension ⋮ Constructive approximate interpolation by neural networks ⋮ A New Function Space from Barron Class and Application to Neural Network Approximation
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Interpolation of scattered data: distance matrices and conditionally positive definite functions
- On functions with bounded \(n\)-th differences
- Translates of multivariate splines
- Convergence properties of radial basis functions
- Multilayer feedforward networks are universal approximators
- Optimal nonlinear approximation
- Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
- Approximation by superpositions of a sigmoidal function
