Gnecco, Giorgio and Kůrková, Věra and Sanguineti, Marcello
*Bounds for Approximate Solutions of Fredholm Integral Equations Using Kernel Networks.*
In:
Artificial Neural Networks and Machine Learning – ICANN 2011.
Lecture Notes in Computer Science
(6791).
Springer, pp. 126-133.
ISBN 978-3-642-21734-0
(2011)

Official URL: http://dx.doi.org/10.1007/978-3-642-21735-7_16

## Abstract

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.

Item Type: | Book Section |
---|---|

Identification Number: | 10.1007/978-3-642-21735-7_16 |

Additional Information: | Proceedings of the 21st International Conference on Artificial Neural Networks (ICANN 2011)held in Espoo, Finland, June 14th-17th, 2011 |

Uncontrolled Keywords: | Radial and kernel networks; approximation of solutions of integral equations by kernel networks; model complexity |

Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |

Research Area: | Computer Science and Applications |

Depositing User: | Giorgio Gnecco |

Date Deposited: | 12 Sep 2013 11:06 |

Last Modified: | 16 Sep 2013 12:03 |

URI: | http://eprints.imtlucca.it/id/eprint/1696 |

### Actions (login required)

Edit Item |