TY  - CHAP
T2  - Artificial Neural Networks ? ICANN 2010
UR  - http://dx.doi.org/10.1007/978-3-642-15825-4_48
A1  - Gnecco, Giorgio
A1  - K?rková, V?ra
A1  - Sanguineti, Marcello
Y1  - 2010///
PB  - Springer
ID  - eprints1669
EP  - 367
TI  - Some Comparisons of Model Complexity in Linear and Neural-Network Approximation
SP  - 358
N2  - 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.
T3  - Lecture Notes in Computer Science
N1  - Proceedings of the 20th International Conference, Thessaloniki, Greece, September 15-18, 2010, Part III

AV  - none
SN  - 978-3-642-15825-4
ER  -