Comparison of worst case errors in linear and neural network approximation

Authors:
V. Kurkova;M. Sanguineti
Affiliations:
Inst. of Comput. Sci., Acad. of Sci. of the Czech Republic, Prague;-
Venue:
IEEE Transactions on Information Theory
Year:
2006

Citing 0
Cited 25

Approximating networks and extended Ritz method for the solution of functional optimization problems

Journal of Optimization Theory and Applications
Fault diagnosis for nonlinear systems using a bank of neural estimators

Computers in Industry - Special issue: Soft computing in industrial applications
On the tractability of multivariate integration and approximation by neural networks

Journal of Complexity
When is approximation by Gaussian networks necessarily a linear process?

Neural Networks
Learning with generalization capability by kernal methods of bounded complexity

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

Journal of Approximation Theory
Estimates of covering numbers of convex sets with slowly decaying orthogonal subsets

Discrete Applied Mathematics
Complexity of Gaussian-radial-basis networks approximating smooth functions

Journal of Complexity
The extended Ritz method for functional optimization: overview and applications to single-person and team optimal decision problems

Optimization Methods & Software
Accuracy of suboptimal solutions to kernel principal component analysis

Computational Optimization and Applications
Learning with generalization capability by kernel methods of bounded complexity

Journal of Complexity
Regularization techniques and suboptimal solutions to optimization problems in learning from data

Neural Computation
Output feedback sliding mode control with support vector machine based observer gain adaptation

CSECS'09 Proceedings of the 8th WSEAS International Conference on Circuits, systems, electronics, control & signal processing
Observer gain adaptation of output feedback sliding mode controller with support vector machine regression

WSEAS Transactions on Systems and Control
Management of water resource systems in the presence of uncertainties by nonlinear approximation techniques and deterministic sampling

Computational Optimization and Applications
A neural network of smooth hinge functions

IEEE Transactions on Neural Networks
Some comparisons of model complexity in linear and neural-network approximation

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Some comparisons of complexity in dictionary-based and linear computational models

Neural Networks
Approximation bound of mixture networks in Lwp spaces

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Improvement on the approximation bound for fuzzy-neural networks clustering method with gaussian membership function

ADMA'05 Proceedings of the First international conference on Advanced Data Mining and Applications
Book review: Adaptive neural network control of robotic manipulators

Automatica (Journal of IFAC)
2011 Special Issue: Can dictionary-based computational models outperform the best linear ones?

Neural Networks
Complexity estimates based on integral transforms induced by computational units

Neural Networks
Suboptimal Solutions to Team Optimization Problems with Stochastic Information Structure

SIAM Journal on Optimization
Regularized vector field learning with sparse approximation for mismatch removal

Pattern Recognition

Quantified Score

Hi-index	754.84

Visualization

Abstract

Sets of multivariable functions are described for which worst case errors in linear approximation are larger than those in approximation by neural networks. A theoretical framework for such a description is developed in the context of nonlinear approximation by fixed versus variable basis functions. Comparisons of approximation rates are formulated in terms of certain norms tailored to sets of basis functions. The results are applied to perceptron networks