TY  - CHAP
EP  - 133
T2  - Artificial Neural Networks and Machine Learning ? ICANN 2011
N1  - Proceedings of the 21st International Conference on Artificial Neural Networks (ICANN 2011)held in Espoo, Finland, June 14th-17th, 2011
ID  - eprints1696
UR  - http://dx.doi.org/10.1007/978-3-642-21735-7_16
TI  - Bounds for Approximate Solutions of Fredholm Integral Equations Using Kernel Networks
AV  - none
KW  - Radial and kernel networks; approximation of solutions of integral equations by kernel networks; model complexity
N2  - Approximation of solutions of integral equations by networks with kernel units is investigated theoretically. There are derived upper bounds on speed of decrease of errors in approximation of solutions of Fredholm integral equations by kernel networks with increasing numbers of units. The estimates are obtained for Gaussian and degenerate kernels.
SN  - 978-3-642-21734-0
Y1  - 2011///
T3  - Lecture Notes in Computer Science
SP  - 126
A1  - Gnecco, Giorgio
A1  - K?rková, V?ra
A1  - Sanguineti, Marcello
PB  - Springer
ER  -