Fast algorithm and implementation of dissimilarity self-organizing maps

DOI10.1016/J.NEUNET.2006.05.002MaRDI QIDQ2506522zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Brieuc Conan-Guez, Fabrice Rossi, Aïcha El Golli

Publication date 10 October 2006

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0709.3461

zbMATH Keywords

clusteringdissimilarity datafast implementationnonlinear projectionpairwise dataproximity dataself-organizing mapunsupervised learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonnumerical algorithms (68W05)

Abstract: In many real world applications, data cannot be accurately represented by vectors. In those situations, one possible solution is to rely on dissimilarity measures that enable sensible comparison between observations. Kohonen's Self-Organizing Map (SOM) has been adapted to data described only through their dissimilarity matrix. This algorithm provides both non linear projection and clustering of non vector data. Unfortunately, the algorithm suffers from a high cost that makes it quite difficult to use with voluminous data sets. In this paper, we propose a new algorithm that provides an important reduction of the theoretical cost of the dissimilarity SOM without changing its outcome (the results are exactly the same as the ones obtained with the original algorithm). Moreover, we introduce implementation methods that result in very short running times. Improvements deduced from the theoretical cost model are validated on simulated and real world data (a word list clustering problem). We also demonstrate that the proposed implementation methods reduce by a factor up to 3 the running time of the fast algorithm over a standard implementation.

Recommendations

• Self-organizing map algorithm and distortion measure
• Rapid learning with parametrized self-organizing maps
• Self-organizing maps by difference of convex functions optimization
• Parallel implementations of self-organizing maps
• Self-organizing maps: Generalizations and new optimization techniques
• A parallel general implementation of Kohonen's self-organizing map algorithm: performance and scalability
• Self-organizing maps
• Self-organizing maps

Cites work

• Classification, clustering, and data mining applications. Proceedings of the meeting of the International Federation of Classification Societies (IFCS), Chicago, IL, USA, July 15--18, 2004.
• Constrained clustering and Kohonen self-organizing maps
• scientific article; zbMATH DE number 3240929 (Why is no real title available?)
• scientific article; zbMATH DE number 3340881 (Why is no real title available?)
• Self-organizing maps
• Self-organizing maps and clustering methods for matrix data
• Self-organizing maps of symbol strings
• Self-organizing maps: Generalizations and new optimization techniques

Cited in

(7)

• Topographic mapping of large dissimilarity data sets
• The new and computationally efficient MIL-SOM algorithm: potential benefits for visualization and analysis of a large-scale high-dimensional clinically acquired geographic data
• Self-organizing hidden Markov model map (SOHMMM)
• scientific article; zbMATH DE number 2090244 (Why is no real title available?)
• scientific article; zbMATH DE number 1406081 (Why is no real title available?)
• A novel data-driven visualization of n-dimensional feasible region using interpretable self-organizing maps (iSOM)
• Self-organizing map for symbolic data

This page was built for publication: Fast algorithm and implementation of dissimilarity self-organizing maps

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2506522)