Exact classification with two-layered perceptrons

P.J. Zwietering, E.H.L. Aarts, J. Wessels

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Samenvatting

We study the capabilities of two-layered perceptrons for classifying exactly a given subset. Both necessary and sufficient conditions are derived for subsets to be exactly classifiable with two-layered perceptrons that use the hard-limiting response function. The necessary conditions can be viewed as generalizations of the linear-separability condition of one-layered perceptrons and confirm the conjecture that the capabilities of two-layered perceptrons are more limited than those of three-layered perceptrons. The sufficient conditions show that the capabilities of two-layered perceptrons extend beyond the exact classification of convex subsets. Furthermore, we present an algorithmic approach to the problem of verifying the sufficiency condition for a given subset.
Originele taal-2Engels
Pagina's (van-tot)143-156
TijdschriftInternational Journal of Neural Systems
Volume3
Nummer van het tijdschrift2
DOI's
StatusGepubliceerd - 1992

Vingerafdruk Duik in de onderzoeksthema's van 'Exact classification with two-layered perceptrons'. Samen vormen ze een unieke vingerafdruk.

Citeer dit