Logo eprints

Some Comparisons of Model Complexity in Linear and Neural-Network Approximation

Gnecco, Giorgio and Kůrková, Věra and Sanguineti, Marcello Some Comparisons of Model Complexity in Linear and Neural-Network Approximation. In: Artificial Neural Networks – ICANN 2010. Lecture Notes in Computer Science (6354). Springer, pp. 358-367. ISBN 978-3-642-15825-4 (2010)

Full text not available from this repository.


Capabilities of linear and neural-network models are compared from the point of view of requirements on the growth of model complexity with an increasing accuracy of approximation. Upper bounds on worst-case errors in approximation by neural networks are compared with lower bounds on these errors in linear approximation. The bounds are formulated in terms of singular numbers of certain operators induced by computational units and high-dimensional volumes of the domains of the functions to be approximated.

Item Type: Book Section
Additional Information: Proceedings of the 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Part III
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Research Area: Computer Science and Applications
Depositing User: Giorgio Gnecco
Date Deposited: 10 Sep 2013 15:08
Last Modified: 16 Sep 2013 12:03
URI: http://eprints.imtlucca.it/id/eprint/1669

Actions (login required)

Edit Item Edit Item