Estimates of Network Complexity and Integral Representations

Authors:
Paul C. Kainen;Věra Kůrková
Affiliations:
Department of Mathematics, Georgetown University, Washington, USA D.C. 20057-1233;Institute of Computer Science, Academy of Sciences of the Czech Republic, Prague 8, Czech Republic
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 8
Cited 0

Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory

Neural Networks
Rate of approximation results motivated by robust neural network learning

COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Estimates of the number of hidden units and variation with respect to half-spaces

Neural Networks
Error Estimates for Approximate Optimization by the Extended Ritz Method

SIAM Journal on Optimization
A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves

Journal of Approximation Theory
Minimization of error functionals over perceptron networks

Neural Computation
Estimates of Approximation Rates by Gaussian Radial-Basis Functions

ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
An integral upper bound for neural network approximation

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Upper bounds on rates of approximation by neural networks are derived for functions representable as integrals in the form of networks with infinitely many units. The bounds are applied to perceptron networks.