Distance-based Multilayer Perceptrons.

Wlodzislaw Duch, Rafal Adamczak and Geerd H.F. Diercksen
Department of Computer Methods, Nicholas Copernicus University,
Grudziadzka 5, 87-100 Torun, Poland.
E-mails: duch,raad@phys.uni.torun.pl;  ghd@mpa-garching.mpg.de

International Conference on Computational Intelligence for Modelling Control and Automation,
17-19 February 1999, Vienna, Austria (in print)


 


Neural network models are presented as special cases of a framework for general Similarity-Based Methods (SBMs). Distance-based multilayer perceptrons (D-MLPs) with non-Euclidean metric functions are described. D-MLPs evaluate similarity to prototypes making the interpretation of the results easier. Renormalization of the input data in the extended feature space brings dramatic changes in the shapes of decision borders. An illustrative example showing these changes is provided.

Paper in gzipped postscript, 413 kB
Paper in uncompressed postscript, 1851 kB