Geometrical Aspects of Discrimination by Multilayer Perceptrons

Salvatore Ingrassia

Journal of Multivariate Analysis, 1999, vol. 68, issue 2, 226-234

Abstract: We investigate some geometrical aspects of the discriminant functions of the kindfp(x)=[summation operator]pk=1 ck[tau](a'kx) for suitable constantsak, ckwhere[tau]is a sigmoidal transformation. This function is realized by a multilayer perceptron with one hidden layer. These results are applied in the analysis of the discriminating power offp. In particular, we prove that the class of finite populations[Omega]1and[Omega]2that can be distinguished byfpis monotonically increasing inpand we give a minimal sufficientpleading to a complete separation between[Omega]1and[Omega]2.

Keywords: Discrimination; multilayer; perceptron; sigmoidal; function. (search for similar items in EconPapers)
Date: 1999
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0047-259X(98)91786-9
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:jmvana:v:68:y:1999:i:2:p:226-234

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Journal of Multivariate Analysis is currently edited by de Leeuw, J.

More articles in Journal of Multivariate Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().