Using Spatio-temporal Correlations to Learn Invariant Object Recognition

Wallis, GM

doi:10.1016/S0893-6080(96)00041-X

Datensatz

DATENSATZ AKTIONENEXPORT

Zur Ablage hinzufügen

Lokale TagsFreigabegeschichteDetailsÜbersicht

Freigegeben

Zeitschriftenartikel

Using Spatio-temporal Correlations to Learn Invariant Object Recognition

MPG-Autoren

/persons/resource/persons84297

Wallis, GM
Department Human Perception, Cognition and Action, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Externe Ressourcen

https://www.sciencedirect.com/science/article/pii/S089360809600041X
(Verlagsversion)

Volltexte (beschränkter Zugriff)

Für Ihren IP-Bereich sind aktuell keine Volltexte freigegeben.

Volltexte (frei zugänglich)

Es sind keine frei zugänglichen Volltexte in PuRe verfügbar

Ergänzendes Material (frei zugänglich)

Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar

Zitation

Wallis, G. (1996). Using Spatio-temporal Correlations to Learn Invariant Object Recognition. Neural networks, 9(9), 1513-1519. doi:10.1016/S0893-6080(96)00041-X.

Zitierlink: https://hdl.handle.net/11858/00-001M-0000-0013-EAF6-B

Zusammenfassung

A competitive network is described which learns to classify objects on the basis of temporal as well as spatial correlations. This is achieved by using a Hebb-like learning rule which is dependent upon prior as well as current neural activity. The rule is shown to be capable of outperforming a supervised rule on the cross validation test of an invariant character recognition task, given a relatively small training set. It is also shown to outperform the supervised version of
Fukushima's Neocognitron (Fukushima, 1980), on a larger training set.