Sökning: L773:0952 813X OR L773:1362 3079 >
Perceptrons with po...
Perceptrons with polynomial post-processing
-
- Sanzogni, L. (författare)
- Mälardalens högskola,Institutionen för matematik och fysik,Griffith University, Australia
-
- Chan, Ringo (författare)
- Griffith University, Australia
-
- Bonner, Richard F. (författare)
- Mälardalens högskola,Institutionen för matematik och fysik,Griffith University, Australia
-
(creator_code:org_t)
- 2000
- 2000
- Engelska.
-
Ingår i: Journal of experimental and theoretical artificial intelligence (Print). - 0952-813X .- 1362-3079. ; 12, s. 57-68
- Relaterad länk:
-
https://urn.kb.se/re...
Abstract
Ämnesord
Stäng
- 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 Mu$ntz-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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Bioinformatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Bioinformatics (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas