Randomized self-organizing map

DOI10.1162/NECO_A_01406zbMATH Open1483.92021arXiv2011.09534OpenAlexW3171235531MaRDI QIDQ5033516FDOQ5033516

Authors: Nicolas P. Rougier, Georgios Is. Detorakis 

Publication date: 23 February 2022

Published in: Neural Computation (Search for Journal in Brave)

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 high-dimensional 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.

Full work available at URL: https://arxiv.org/abs/2011.09534

Recommendations

• Learning a Self-organizing Map Model on a Riemannian Manifold
• Self-organizing maps: Generalizations and new optimization techniques
• scientific article; zbMATH DE number 2013281
• Topology selection for self-organizing maps
• Self organizing MAPS: understanding, measuring and reducing variability

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Cited In (4)

• Probabilistic self-organizing map and radial basis function networks
• RT-GSOM: rough tolerance growing self-organizing map
• Rough self organizing map
• Title not available (Why is that?)

This page was built for publication: Randomized self-organizing map

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033516)