Extended Network for Backpropagation Algorithm

Mircea Petrini ()
Additional contact information
Mircea Petrini: University of Petroşani, Romania

Annals of the University of Petrosani, Economics, 2012, vol. 12, issue 4, 177-184

Abstract: This paper presents the backpropagation algorithm based on an extended network approach in which the algorithm reduces to a graph labeling problem. This method is not only more general than the usual analytical derivations, which handle only the case of special network topologies, but also much easier to follow. It also shows how the algorithm can be efficiently implemented in computing systems in which only local information can be transported through the network.

Keywords: Artificial Neural Network (ANN); backpropagation; extended network; feed-forward computation; training pattern (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2012
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://upet.ro/annals/economics/pdf/2012/part4/Petrini-1.pdf (application/pdf)

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:pet:annals:v:12:y:2012:i:4:p:177-184

Access Statistics for this article

More articles in Annals of the University of Petrosani, Economics from University of Petrosani, Romania
Bibliographic data for series maintained by Imola Driga ().