On the performance of neuronal matching algorithms.

Neural networks : the official journal of the International Neural Network Society

PubMedID: 12662721

Würtz RP, Konen W, Behrmann KO. On the performance of neuronal matching algorithms. Neural Netw. 1999;12(1):127-134.
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.