On the performance of neuronal matching algorithms

• Published in: Neural networks Vol. 12; no. 1; pp. 127 - 134
• Main Authors: Würtz, Rolf P, Konen, Wolfgang, Behrmann, Kay-Ole
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 1999; Elsevier Science
• Subjects: Algorithmics. Computability. Computer arithmetics; Applied sciences; Artificial intelligence; Complexity; Computer science; control theory; systems; Connectionism. Neural networks; Convergence speed; Correspondence problem; Dynamic link matching; Exact sciences and technology; Self-organizing map; Symmetry recognition; Theoretical computing; Dynamic link matching; Correspondence problem; Symmetry recognition; Self-organizing map; Convergence speed; Complexity; Self organization; Maps; Theoretical study; Correspondence principle; Dynamic model; Link
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/S0893-6080(98)00112-9

For a solution of the visual correspondence problem we have modified the Self Organizing Map (SOM) to map image planes onto another in a neighborhood- and feature-preserving way. We have investigated the convergence speed of this SOM and Dynamic Link Matching (DLM) on a benchmark problem for the solution of which both algorithms are good candidates. We show that even after careful parameter adjustment the SOM needs a large number of simple update steps and DLM a small number of complicated ones. The results are consistent with an exponential vs. polynomial scaling behavior with increased pattern size. Finally, we present and motivate a rule for adjusting the parameters of DLM for all problem sizes, which we could not find for SOM.