Self-organizing maps in sequence processing

No Thumbnail Available
Journal Title
Journal ISSN
Volume Title
Doctoral thesis (article-based)
Checking the digitized thesis and permission for publishing
Instructions for the author
Degree programme
71, [59]
Helsinki University of Technology Laboratory of Computational Engineering publications. Report B, 32
Models are abstractions of observed real world phenomena or processes. A good model captures the essential properties of the modeled phenomena. In the statistical learning paradigm the processes that generate observations are assumed unknown and too complex for analytical modeling, thus the models are trained from more general templates with measured observations. A substantial part of the processes we seek to model have temporal dependencies between observations thus defining templates that can account for these dependencies improves their ability to capture the properties of such processes. In this work we discuss using the self organizing map with sequentially dependent data. Self-Organizing map (SOM) is perhaps the most popular non supervised neural network model that has found varied applications in the field of data mining for example. The original SOM paradigm, however, considers independent data, where context of a sample does not influence its interpretation. However, throwing away the temporal context of an observation when we know we are dealing with sequential data seems wasteful. Consequently methods for incorporating time into the SOM paradigm have been rather extensively studied. Such models if powerful enough would be very usable when tracking dynamic processes. In this work a Self-Organizing map for temporal sequence processing dubbed Recurrent Self-Organizing Map (RSOM) was proposed and analyzed. The model has been used in time series prediction combined with local linear models. Deeper analysis provides insight into how much and what kind of contextual information the model is able to capture. The other topic covered by the publications in a sense considers an inverse problem. In this topic SOM was used to create sequential dependence and order into initially unordered data by modeling a surface and creating a path over the surface for a surface manipulating robot.
self-organizing maps, temporal sequence processing
Other note
  • Varsta, M., and Koikkalainen, P. (1996) Surface Modeling and Robot Path Generation Using Self-Organization. In Proceedings of ICPR '96, pages 30-34. IEEE.
  • Koikkalainen, P., and Varsta, M. (1996) Robot Path generation for surface processing applications via neural networks. In Proceedings of the SPIE, Vol. 2904, pages 66-73. SPIE.
  • Varsta, M., Heikkonen, J., and Millán, J. del R. (1997) Epileptic Activity Detection in EEG with Neural Networks. In Proceedings of the 1997 International Conference on Engineering Applications of Neural Networks, pages 179-186. The Royal Institute of Technology, Stockholm.
  • Varsta, M., Millán, J. del R., and Heikkonen, J., (1997) A Recurrent Self Organizing Map for Temporal Sequence Processing. In ICANN'97: International Conference on Artificial Neural Networks, LNCS vol. 1327, pages 421-426. Springer.
  • Koskela, T., Varsta, M., Heikkonen, J., and Kaski, K. (1998) Temporal Sequence Processing using Recurrent SOM. In KES '98: Proceedings of the Second International Conference on Knowledge Based Engineering Systems, vol. 1, pages 290-296. IEEE.
  • Varsta, M., Heikkonen, J., Lampinen, J., and Millán, J. del R. (2001) Temporal Kohonen Map and the Recurrent Self-Organizing Map: Analytical and Experimental Comparison. Neural Processing Letters, Vol. 13, pages 237-251, Kluwer Academic Publishers.
Permanent link to this item