NELGNov 18, 2020

Randomized Self Organizing Map

arXiv:2011.09534v16 citations
AI Analysis

This work addresses the problem of improving the flexibility and robustness of self-organizing maps for researchers and practitioners working with high-dimensional data.

This paper introduces a variation of the self-organizing map (SOM) algorithm where neurons are randomly placed on a 2D manifold using a blue noise distribution. This approach allows for more flexible self-organization, particularly with high-dimensional data, and demonstrates the algorithm's ability to reorganize itself after neural lesions or neurogenesis.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes