Mapping error in the parallel realizations of SAMANN algorithm
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 unsupervi...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Vilnius University Press
2004-12-01
|
Series: | Lietuvos Matematikos Rinkinys |
Subjects: | |
Online Access: | https://www.journals.vu.lt/LMR/article/view/32221 |
_version_ | 1797194381300596736 |
---|---|
author | Viktor Medvedev Gintautas Dzemyda |
author_facet | Viktor Medvedev Gintautas Dzemyda |
author_sort | Viktor Medvedev |
collection | DOAJ |
description |
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.
|
first_indexed | 2024-03-07T15:40:24Z |
format | Article |
id | doaj.art-3ae7099a05e2475babe040450d7f33a8 |
institution | Directory Open Access Journal |
issn | 0132-2818 2335-898X |
language | English |
last_indexed | 2024-04-24T05:55:23Z |
publishDate | 2004-12-01 |
publisher | Vilnius University Press |
record_format | Article |
series | Lietuvos Matematikos Rinkinys |
spelling | doaj.art-3ae7099a05e2475babe040450d7f33a82024-04-23T09:02:12ZengVilnius University PressLietuvos Matematikos Rinkinys0132-28182335-898X2004-12-0144spec.10.15388/LMR.2004.32221Mapping error in the parallel realizations of SAMANN algorithmViktor Medvedev0Gintautas Dzemyda1Institute of Mathematics and InformaticsInstitute of Mathematics and Informatics 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. https://www.journals.vu.lt/LMR/article/view/32221neutral networksSAMANN algorithmSammon's mappingvisualization |
spellingShingle | Viktor Medvedev Gintautas Dzemyda Mapping error in the parallel realizations of SAMANN algorithm Lietuvos Matematikos Rinkinys neutral networks SAMANN algorithm Sammon's mapping visualization |
title | Mapping error in the parallel realizations of SAMANN algorithm |
title_full | Mapping error in the parallel realizations of SAMANN algorithm |
title_fullStr | Mapping error in the parallel realizations of SAMANN algorithm |
title_full_unstemmed | Mapping error in the parallel realizations of SAMANN algorithm |
title_short | Mapping error in the parallel realizations of SAMANN algorithm |
title_sort | mapping error in the parallel realizations of samann algorithm |
topic | neutral networks SAMANN algorithm Sammon's mapping visualization |
url | https://www.journals.vu.lt/LMR/article/view/32221 |
work_keys_str_mv | AT viktormedvedev mappingerrorintheparallelrealizationsofsamannalgorithm AT gintautasdzemyda mappingerrorintheparallelrealizationsofsamannalgorithm |