Document Detail

Generalized hamming networks and applications.
MedLine Citation:
PMID:  15949918     Owner:  NLM     Status:  MEDLINE    
In this paper the classical Hamming network is generalized in various ways. First, for the Hamming maxnet, a generalized model is proposed, which covers under its umbrella most of the existing versions of the Hamming Maxnet. The network dynamics are time varying while the commonly used ramp function may be replaced by a much more general non-linear function. Also, the weight parameters of the network are time varying. A detailed convergence analysis is provided. A bound on the number of iterations required for convergence is derived and its distribution functions are given for the cases where the initial values of the nodes of the Hamming maxnet stem from the uniform and the peak distributions. Stabilization mechanisms aiming to prevent the node(s) with the maximum initial value diverging to infinity or decaying to zero are described. Simulations demonstrate the advantages of the proposed extension. Also, a rough comparison between the proposed generalized scheme as well as the original Hamming maxnet and its variants is carried out in terms of the time required for convergence, in hardware implementations. Finally, the other two parts of the Hamming network, namely the competitors generating module and the decoding module, are briefly considered in the framework of various applications such as classification/clustering, vector quantization and function optimization.
Konstantinos Koutroumbas; Nicholas Kalouptsidis
Related Documents :
16873518 - Inferring functional pathways from multi-perturbation data.
17524148 - A hybrid multiscale monte carlo algorithm (hymsmc) to cope with disparity in time scale...
15697438 - Finding community structure in very large networks.
12850038 - Automatic basis selection techniques for rbf networks.
16351148 - Sign constraints improve the detection of differences between complex spectral data set...
22262418 - A scandinavian experience of register collaboration: the nordic arthroplasty register a...
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Neural networks : the official journal of the International Neural Network Society     Volume:  18     ISSN:  0893-6080     ISO Abbreviation:  Neural Netw     Publication Date:  2005 Sep 
Date Detail:
Created Date:  2005-09-09     Completed Date:  2005-11-14     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8805018     Medline TA:  Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  896-913     Citation Subset:  IM    
Institute for Space Applications and Remote Sensing, National Observatory of Athens, Metaxa and V. Pavlou, Palaia Penteli, 15236, Athens, Greece.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Artificial Intelligence
Neural Networks (Computer)*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Novel multiple 5'-amino-modified primer for DNA microarrays.
Next Document:  Reduction in flow artifacts by using interleaved data acquisition in segmented balanced steady-state...