Number of the records: 1
Comparison of Rates of Linear and Neural Network Approximation
- 1.0403807 - UIVT-O 20000033 RIV US eng C - Conference Paper (international conference)
Kůrková, Věra - Sanguineti, M.
Comparison of Rates of Linear and Neural Network Approximation.
IJCNN 2000. Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. Los Alamitos: IEEE Computer Society, 2000, s. 277-282. ISBN 0-7695-0619-4.
[IJCNN 2000. Como (IT), 24.07.2000-27.07.2000]
R&D Projects: GA ČR GA201/99/0092
Institutional research plan: AV0Z1030915
Keywords : linear and neural networks approximation * Kolmogorov width * dimension-independent rates of approximation * perceptron networks
Subject RIV: BA - General Mathematics
Some mathematical tools for comparison of rates of fixed versus variable basis function approximation are presented. Sets of multivariable functions, for which lower bounds on worst-case errors in approximation by n-dimensional linear subspaces are larger than upper bounds on such errors in approximation by perceptron networks with n hidden units are described.
Permanent Link: http://hdl.handle.net/11104/0124098
Number of the records: 1