Performance of back propagation networks for associative database retrieval

This item is provided by the institution :
Technological Educational Institute of Athens
Repository :
Ypatia - Institutional Repository
see the original item page
in the repository's web site and access all digital files if the item*

1989 (EN)
Performance of back propagation networks for associative database retrieval (EN)

Βασιλάς, Νικόλαος (EL)
Cherkassky, Vladimir (EN)

Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Πληροφορικής Τ.Ε. (EL)

Back-propagation networks have been successfully used to perform a variety of input-output mapping tasks for recognition, generalization, and classification. In spite of this method's popularity, virtually nothing is known about its saturation/capacity and, in more general terms, about its performance as an associative memory. The authors address these issues using associative database retrieval as an original application domain. Experimental results show that the quality of recall and the network capacity are very significantly affected by the network topology (the number of hidden units), data representation (encoding), and the choice of learning parameters. On the basis of their results and the fact that back-propagation learning is not recursive, the authors conclude that back-propagation networks can be used mainly as read-only associative memories and represent a poor choice for read-and-write associative memories. (EN)


propagation networks (EN)
Electric network topology (EN)
τοπολογία δικτύου (EN)
δίκτυα διάδοσης (EN)
συνδυαστική ανάκτηση της βάσης δεδομένων (EN)
associative database retrieval (EN)

ΤΕΙ Αθήνας (EL)
Technological Educational Institute of Athens (EN)




DOI: 10.1109/IJCNN.1989.118562


*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)