de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Datenschutzhinweis Impressum Kontakt
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Zeitschriftenartikel

Threshold Complex-Valued Neural Associative Memory

MPG-Autoren
Es sind keine MPG-Autoren in der Publikation vorhanden
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Zheng, P. (2014). Threshold Complex-Valued Neural Associative Memory. IEEE Transactions on Neural Networks and Learning Systems, 25(9), 1714-1718. doi:10.1109/TNNLS.2013.2280573.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-001A-14C2-6
Zusammenfassung
In this brief, threshold complex-valued neural associative memory is proposed for information retrieval. The introduction of threshold improves network performance by excluding rotated patterns from spurious memories. A design method for constructing different types of network is developed based on complex matrix decomposition, which is capable of designing nonthreshold, threshold, non-Hermitian, and Hermitian networks. Further, we illustrate the performance of the proposed method by reconstructing noisy 256 grayscale and true color images. The results show that constructed networks can work efficiently, threshold networks have better performance than nonthreshold ones and networks with small asymmetry in weight matrix function as well as Hermitian ones.