Randomized Self Organizing Map - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Neural Computation Year : 2021

Randomized Self Organizing Map

Abstract

We propose a variation of the self organizing map algorithm by considering the random placement of neurons on a two-dimensional manifold, following a blue noise distribution from which various topologies can be derived. These topologies possess random (but controllable) discontinuities that allow for a more flexible self-organization, especially with highdimensional data. The proposed algorithm is tested on one-, two-and three-dimensions tasks as well as on the MNIST handwritten digits dataset and validated using spectral analysis and topological data analysis tools. We also demonstrate the ability of the randomized self-organizing map to gracefully reorganize itself in case of neural lesion and/or neurogenesis.
Fichier principal
Vignette du fichier
article-arxiv.pdf (10.76 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03017448 , version 1 (20-11-2020)

Identifiers

Cite

Nicolas P. Rougier, Georgios Is Detorakis. Randomized Self Organizing Map. Neural Computation, In press, ⟨10.1162/neco_a_01406⟩. ⟨hal-03017448⟩
63 View
138 Download

Altmetric

Share

Gmail Facebook X LinkedIn More