Title
How Fast can Neuronal Algorithms Match Patterns
Abstract
. We investigate the convergence speed of the Self OrganizingMap (SOM) and Dynamic Link Matching (DLM) on a benchmark problemfor the solution of which both algorithms are good candidates. Weshow that the SOM needs a large number of simple update steps andDLM a small number of complicated ones. A comparison of the actualnumber of floating point operations hints at an exponential vs. polynomialscaling behavior with increased pattern size. DLM turned out to bemuch less sensitive to...
Year
DOI
Venue
1996
10.1007/3-540-61510-5_28
ICANN
Keywords
Field
DocType
algorithms match patterns,floating point
Convergence (routing),Small number,Exponential function,Polynomial,Pattern recognition,Floating point,Computer science,Algorithm,Dynamic link matching,Artificial intelligence,Scaling
Conference
ISBN
Citations 
PageRank 
3-540-61510-5
0
0.34
References 
Authors
4
7
Name
Order
Citations
PageRank
Rolf P. Würtz132847.01
Wolfgang Konen219335.06
kayole behrmann391.72
Christoph von der Malsburg41190326.77
W von Seelen5503140.13
jan c vorbruggen600.34
Bernhard Sendhoff72272240.31