Ruhr-Universität Bochum zum Inhalt Startseite der RUB pix
Startseite UniStartseite
Überblick UniÜberblick
A-Z UniA-Z
Suche UniSuche
Kontakt UniKontakt

pix
 
Das Siegel
Naturwissenschaften Ingenieurwissenschaften Geisteswissenschaften Medizinische Einrichtungen Zentrale Einrichtungen
pix
 
pix Lehrstuhl Mathematik & Informatik
VC Dimension Bounds for Product Unit Networks
 
 
 
Unser Angebot: Mitarbeiter | Forschung | Lehre   
pix
Startseite » Mitarbeiter » M. Schmitt » VC Dimension Bounds for Product Unit Networks

pix pix VC Dimension Bounds for Product Unit Networks
A product unit is a formal neuron that multiplies its input values instead of summing them. Furthermore, it has weights acting as exponents instead of being factors. We investigate the complexity of learning for networks containing product units. We establish bounds on the Vapnik-Chervonenkis (VC) dimension that can be used to assess the generalization capabilities of these networks. In particular, we show that the VC dimension for these networks is not larger than the best known bound for sigmoidal networks. For higher-order networks we derive upper bounds that are independent of the degree of these networks. We also contrast these results with lower bounds.

 
 
Zum Seitenanfang  Seitenanfang | Diese Seite drucken
Letzte Änderung: 03.02.2003 | Ansprechpartner: Webmaster