|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 5 van 8 gevonden artikelen
| Titel: |
Perceptrons with polynomial post-processing |
| Auteur: |
Sanzogni, Louis Chan, Ringo Bonner, Richard F. |
| Verschenen in: |
Journal of experimental & theoretical artificial intelligence |
| Paginering: | Jaargang 12 (2000) nr. 1 pagina's 57-68 |
| Jaar: |
2000-01-01 |
| Inhoud: |
We introduce tensor product neural networks, composed of a layer of univariate neurons followed by a net of polynomial post-processing. We look at the general approximation properties of these networks observing in particular their relationship to the Stone-Weierstrass theorem for uniform function algebras. The implementation of the post-processing as a two-layer network, with logarithmic and exponential neurons leads to potentially important 'generalized' product networks, which however require a complex approximation theory of Muntz-Szasz-Ehrenpreis type. A back-propagation algorithm for product networks is presented and used in three computational experiments. In particular, approximation by a sigmoid product network is compared to that of a single layer radial basis network, and a multiple layer sigmoid network. An additional experiment is conducted, based on an operational system, to further demonstrate the versatility of the architecture. |
| Uitgever: |
Taylor & Francis |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 5 van 8 gevonden artikelen
| << vorige | volgende >> |