On tractability of neural-network approximation

Authors:
Paul C. Kainen;Věra Kůrková;Marcello Sanguineti
Affiliations:
Department of Mathematics, Georgetown University, Washington, D.C.;Institute of Computer Science, Academy of Sciences of the Czech Republic, Prague 8, Czech Republic;Department of Communications, Computer, and System Sciences, University of Genoa, Genova, Italy
Venue:
ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Year:
2009

Citing 12
Cited 1

Rate of approximation results motivated by robust neural network learning

COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Tractability and strong tractability of linear multivariate problems

Journal of Complexity
Approximation and learning of convex superpositions

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Estimates of the number of hidden units and variation with respect to half-spaces

Neural Networks
Representations and rates of approximation of real-valued Boolean functions by neural networks

Neural Networks
Complexity and information

Complexity and information
Dynamic Programming

Dynamic Programming
Big Omicron and big Omega and big Theta

ACM SIGACT News
On the tractability of multivariate integration and approximation by neural networks

Journal of Complexity
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
Complexity of Gaussian-radial-basis networks approximating smooth functions

Journal of Complexity

2011 Special Issue: Can dictionary-based computational models outperform the best linear ones?

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The tractability of neural-network approximation is investigated. The dependence of worst-case errors on the number of variables is studied. Estimates for Gaussian radial-basis-function and perceptron networks are derived.