It is based on a grid (see initGrid) which is part of the
parameters given to the algorithm (see initSOM and
trainSOM). Many graphs can help you with the results (see
plot.somRes).
| Package: |
| SOMbrero |
| Type: |
| Package |
| Version: |
| 1.2 |
| Date: |
| 2016-09-02 |
Several variants able to handle non-vectorial data are also implemented in their
stochastic versions: type="korresp" for contingency tables, as described
in Cottrel et al., 1993 (with the observation weights defined in Cottrel and
Letremy, 2005) and type="relational" for dissimilarity data, as described
in Olteanu and Villa-Vialaneix, 2015a with the fast implementation of Mariette
et al., 2016. A special focus has been put on representing graphs, as
described in Olteanu and Villa-Vialaneix, 2015b.
Cottrell, M., Letremy, P., Roy, E. (1993) Analyzing a contingency table with Kohonen maps: a Factorial Correspondence Analysis. In: Proceedings of IWANN'93, J. Cabestany, J. Mary, A. Prieto (Eds.), Lecture Notes in Computer Science, Springer-Verlag, 305--311.
Cottrell, M., Letremy, P. (2005) How to use the Kohonen algorithm to simultaneously analyse individuals in a survey. Neurocomputing, 21, 119--138.
Letremy, P. (2005) Programmes bases sur l'algorithme de Kohonen et dedies a l'analyse des donnees. SAS/IML programs for 'korresp'. http://samos.univ-paris1.fr/Programmes-bases-sur-l-algorithme.
Mariette, J. and Rossi, F. and Olteanu, M. and Mariette, J. (2016) Fast implementation of on-line relation SOM. Technical report.
Olteanu, M., Villa-Vialaneix, N. (2015a) On-line relational and multiple relational SOM. Neurocomputing, 147, 15-30.
Olteanu, M., Villa-Vialaneix, N. (2015b) Using SOMbrero for clustering and visualizing graphs. Journal de la Societe Francaise de Statistique. Under revision.
Rossi, F. (2013) yasomi: Yet Another Self-Organising Map Implementation. R package, version 0.3. https://github.com/fabrice-rossi/yasomi
initGrid, trainSOM, plot.somRes and
sombreroGUI.