Are they really neighbors? A statistical analysis of the SOM algorithm output

Eric de Bodt, Marie Cottrell, Michel Verleysen
Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, PMLR R3:87-92, 2001.

Abstract

One of the attractive features of Self-Organizing Maps (SOM) is the so-called "topological preservation property": observations that are close to each other in the input space (at least locally) remain close to each other in the SOM. In this work, we propose the use of a bootstrap scheme to construct a statistical significance test of the observed proximity among individuals in the SOM.

Cite this Paper


BibTeX
@InProceedings{pmlr-vR3-bodt01a, title = {Are they really neighbors? {A} statistical analysis of the {SOM} algorithm output}, author = {de Bodt, Eric and Cottrell, Marie and Verleysen, Michel}, booktitle = {Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics}, pages = {87--92}, year = {2001}, editor = {Richardson, Thomas S. and Jaakkola, Tommi S.}, volume = {R3}, series = {Proceedings of Machine Learning Research}, month = {04--07 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r3/bodt01a/bodt01a.pdf}, url = {http://proceedings.mlr.press/r3/bodt01a.html}, abstract = {One of the attractive features of Self-Organizing Maps (SOM) is the so-called "topological preservation property": observations that are close to each other in the input space (at least locally) remain close to each other in the SOM. In this work, we propose the use of a bootstrap scheme to construct a statistical significance test of the observed proximity among individuals in the SOM.}, note = {Reissued by PMLR on 31 March 2021.} }
Endnote
%0 Conference Paper %T Are they really neighbors? A statistical analysis of the SOM algorithm output %A Eric de Bodt %A Marie Cottrell %A Michel Verleysen %B Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2001 %E Thomas S. Richardson %E Tommi S. Jaakkola %F pmlr-vR3-bodt01a %I PMLR %P 87--92 %U http://proceedings.mlr.press/r3/bodt01a.html %V R3 %X One of the attractive features of Self-Organizing Maps (SOM) is the so-called "topological preservation property": observations that are close to each other in the input space (at least locally) remain close to each other in the SOM. In this work, we propose the use of a bootstrap scheme to construct a statistical significance test of the observed proximity among individuals in the SOM. %Z Reissued by PMLR on 31 March 2021.
APA
de Bodt, E., Cottrell, M. & Verleysen, M.. (2001). Are they really neighbors? A statistical analysis of the SOM algorithm output. Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R3:87-92 Available from http://proceedings.mlr.press/r3/bodt01a.html. Reissued by PMLR on 31 March 2021.

Related Material