de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Threshold Complex-Valued Neural Associative Memory

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons133467

Zheng,  P
Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Zheng, P. (2013). Threshold Complex-Valued Neural Associative Memory. IEEE Transactions on Neural Networks and Learning Systems, Epub ahead. doi:10.1109/TNNLS.2013.2280573.


Cite as: http://hdl.handle.net/11858/00-001M-0000-001A-14C2-6
Abstract
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.