Skip to Main content Skip to Navigation
Journal articles

Randomized Self Organizing Map

Nicolas Rougier 1 Georgios Detorakis 2
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
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.
Document type :
Journal articles
Complete list of metadata
Contributor : Nicolas P. Rougier Connect in order to contact the contributor
Submitted on : Friday, November 20, 2020 - 8:44:35 PM
Last modification on : Tuesday, January 4, 2022 - 6:17:26 AM


Files produced by the author(s)


  • HAL Id : hal-03017448, version 1
  • ARXIV : 2011.09534



Nicolas Rougier, Georgios Detorakis. Randomized Self Organizing Map. Neural Computation, Massachusetts Institute of Technology Press (MIT Press), In press. ⟨hal-03017448⟩



Les métriques sont temporairement indisponibles