RECURSIVE SELF-ORGANIZING NETWORKS FOR PROCESSING TREE STRUCTURES - Empirical Comparison

Pavol Vančo, Igor Farkaš

Abstract

During the last decade, self-organizing neural maps have been extended to more general data structures, such as sequences or trees. To gain insight into how these models learn the tree data, we empirically compare three recursive versions of the self-organizing map – SOMSD, MSOM and RecSOM – using two data sets with the different levels of complexity: binary syntactic trees and ternary trees of linguistic propositions. We evaluate the models in terms of proposed measures focusing on unit’s receptive fields and on model’s capability to distinguish the trees either in terms of separate winners or distributed map output activation vectors. The models learn to topographically organize the data but differ in how they balance the effects of labels and the tree structure in representing the trees. None of the models could successfully distinguish all vertices by assigning them unique winners, and only RecSOM, being computationally the most expensive model regarding the context representation, could unambiguously distinguish all trees in terms of distributed map output activation.

References

  1. Chappell, G. J. and Taylor, J. G. (1993). The temporal Kohonen map. Neural Networks, 6:441-445.
  2. de A. Barreto, G., Araújo, A., and Kremer, S. (2003). A taxonomy of spatiotemporal connectionist networks revisited: The unsupervised case. Neural Computation, 15:1255-1320.
  3. Hagenbuchner, M., Sperduti, A., and Tsoi, A. (2003). A self-organizing map for adaptive processing of structured data. IEEE Transactions on Neural Networks, 14(3):491-505.
  4. Hammer, B., Micheli, A., Sperduti, A., and Strickert, M. (2004a). Recursive self-organizing network models. Neural Networks, 17(8-9):1061-1085.
  5. Hammer, B., Micheli, A., Strickert, M., and Sperduti, A. (2004b). A general framework for unsupervised processing of structured data. Neurocomputing, 57:3-35.
  6. Kohonen, T. (1990). The self-organizing map. Proceedings of the IEEE, 78(9):1464-1480.
  7. Koskela, T., Varsta, M., Heikkonen, J., and Kaski, K. (1998). Time series prediction using recurrent SOM with local linear models. International Journal of Knowledge-Based Intelligent Eng. Systems, 2(1):60- 68.
  8. Strickert, M. and Hammer, B. (2005). Merge SOM for temporal data. Neurocomputing, 64:39-72.
  9. Tin?o, P., Farkas?, I., and van Mourik, J. (2006). Dynamics and topographic organization in recursive selforganizing map. Neural Computation, 18:2529-2567.
  10. Voegtlin, T. (2002). Recursive self-organizing maps. Neural Networks, 15(8-9):979-992.
  11. Pollack, J. (1990). Recursive distributed representations. Artificial Intelligence, 46(1-2):77-105.
  12. Fodor, J.A., and Pylyshyn, Z.W. (1988). Connectionism and cognitive architecture: A critical analysis. Cognition, 28: 3-71.
  13. Hammer, B. (2003). Perspectives on learning symbolic data with connectionistic systems. In: Adaptivity and Learning, Springer, 141-160.
Download


Paper Citation


in Harvard Style

Vančo P. and Farkaš I. (2009). RECURSIVE SELF-ORGANIZING NETWORKS FOR PROCESSING TREE STRUCTURES - Empirical Comparison . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 459-466. DOI: 10.5220/0002320104590466


in Bibtex Style

@conference{icnc09,
author={Pavol Vančo and Igor Farkaš},
title={RECURSIVE SELF-ORGANIZING NETWORKS FOR PROCESSING TREE STRUCTURES - Empirical Comparison},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={459-466},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002320104590466},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - RECURSIVE SELF-ORGANIZING NETWORKS FOR PROCESSING TREE STRUCTURES - Empirical Comparison
SN - 978-989-674-014-6
AU - Vančo P.
AU - Farkaš I.
PY - 2009
SP - 459
EP - 466
DO - 10.5220/0002320104590466