Mapping error in the parallel realizations of SAMANN algorithm
Articles
Viktor Medvedev
Institute of Mathematics and Informatics
Gintautas Dzemyda
Institute of Mathematics and Informatics
Published 2004-12-17
https://doi.org/10.15388/LMR.2004.32221
PDF

Keywords

neutral networks
SAMANN algorithm
Sammon's mapping
visualization

How to Cite

Medvedev, V. and Dzemyda, G. (2004) “Mapping error in the parallel realizations of SAMANN algorithm”, Lietuvos matematikos rinkinys, 44(spec.), pp. 649–654. doi:10.15388/LMR.2004.32221.

Abstract

 In this paper we discuss the visualization of multidimensional vectors. A well-known procedure for mapping data from a high-dimensional space onto a lower-dimensional one is Sammon's mapping. This algorithm preserves as well as possible all inter-pattern distances. We investigate an unsupervised back-propagation algorithm to train a multilayer feed-forward neural network (SAMANN) to perform the Sammoil's nonlinear projection and propose a parallel algorithm for SAMANN network.

 

PDF
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Downloads

Download data is not yet available.