Dynamics and topographic organization of recursive self-organizing maps


Recently there has been an outburst of interest in extending topographic maps of vectorial data to more general data structures, such as sequences or trees. However, there is no general consensus as to how best to process sequences using topographicmaps, and this topic remains an active focus of neurocomputational research. The representational capabilities and internal representations of the models are not well understood. Here, we rigorously analyze a generalization of the self-organizingmap (SOM) for processing sequential data, recursive SOM (RecSOM) (Voegtlin, 2002), as a nonautonomous dynamical system consisting of a set of fixed input maps. We argue that contractive fixed-input maps are likely to produce Markovian organizations of receptive fields on the RecSOM map. We derive bounds on parameter β (weighting the importance of importing past information when processing sequences) under which contractiveness of the fixed-input maps is guaranteed. Some generalizations of SOM contain a dynamic module responsible for processing temporal contexts as an integral part of the model. We show that Markovian topographic maps of sequential data can be produced using a simple fixed (nonadaptable) dynamic module externally feeding a standard topographic model designed to process static vectorial data of fixed dimensionality (e.g., SOM). However, by allowing trainable feedback connections, one can obtain Markovian maps with superior memory depth and topography preservation. We elaborate on the importance of non-Markovian organizations in topographic maps of sequential data. © 2006 Massachusetts Institute of Technology.

Publication DOI: https://doi.org/10.1162/neco.2006.18.10.2529
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: © 2006 Massachusetts Institute of Technology. Dynamics and Topographic Organization of Recursive Self-Organizing Maps Peter Tiňo, Igor Farkaš, and Jort van Mourik Neural Computation 2006 Vol. 18, 2529-2567
Uncontrolled Keywords: topographic maps,vectorial data,general data structures,sequences,Self-Organizing Map,sequential data,Recursive SOM,non-autonomous dynamical system,Markovian organizations,receptive fields,Artificial Intelligence,Control and Systems Engineering,Neuroscience(all)
Publication ISSN: 1530-888X
Last Modified: 15 May 2024 07:07
Date Deposited: 07 Jan 2010 14:11
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
http://www.mitp ... ls.org/loi/neco (Publisher URL)
PURE Output Type: Article
Published Date: 2006-10
Authors: Tino, Peter
Farkas, Igor
van Mourik, Jort (ORCID Profile 0000-0002-3172-2714)



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record