Abstract
We generalize a class of neural network models that extend the Kohonen Self-Organising Map (SOM) algorithm into the sequential and temporal domain using recurrent connections. Behaviour of the class of Activation-based Recursive Self-Organising Maps (ARSOM) is discussed with respect to the choice of transfer function and parameter settings. By comparing performances to existing benchmarks we demonstrate the robustness and systematicity of the ARSOM models, thus opening the door to practical applications.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Abbreviations
- ARSOM:
-
– Activation-based Recursive Self-Organizing Map
- BMU:
-
– Best Matching Unit
- SOM:
-
– Self-Organizing Map
- TF:
-
– Transfer Function
References
Barreto G., De A., Araujo A.F.R. (2001): Time in self-organizing maps: an overview of models. International Journal of Computer Research. Special Issue on Neural Networks: Past, Present and Future 10(2): 139–179
Bingham, E. and Mannila, H.: Random projection in dimensionality reduction: Applications to image and text data. In: Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2001), August 26–29, pp. 245–250, San Francisco, CA, USA, 2001.
Chappell G.J., Taylor J.G. (1993): The temporal Kohonen map. Neural Networks 6(3): 441–445
Elman J. (1990): Finding structure in time. Cognitive Science 14, 179–211
Hertz, J., Krogh, A. and Palmer, R.: Introduction to the theory of neural computation. Reading, MA: A Lecture Notes volume in the Santa Fe Institute Studies in the Sciences of Complexity, Perseus Books, Reading, MA, 1991.
Jordan, M.: Attractor Dynamics and parallellism in a connectionist sequential machine. In: Proceedings of the Eight Annual Meeting of the Cognitive Science Society, Erlbaum, Hillsdale, 1986.
Jordan, M.: I. Serial order: A parallel processing approach. University of California, Center for Human Information Processing, ICS Report 8604, San Diego, 1986.
Kaipainen, M., Papadopoulos, P. and Karhu, P.: MuSeq recurrent oscillatory self- organizing map. Classification and entrainment of temporal feature spaces. In: Proceedings of WSOM’97 Workshop on Self-Organizing Maps 1997, Espoo, Finland, 1997.
Kaipainen M., Karhu P. (2000): Bringing knowing-when and knowing-what together. periodically tuned categorization and category-based timing modeled with the recurrent oscillatory self-organizing map (ROSOM). Minds and Machines 10, 203–229
Kaipainen, M. and Ilmonen, T.: Period detection and representation by recurrent oscillatory self-organizing map, Neurocomputing 55(3–4), 699–710 [Special Issue: Evolving solution with Neural Networks. ed. A. Fanni and A. Uncini].
Kangas, J.: Time-delayed self-organizing maps. In: Proceedings IEEE/INNS International Joint Conference on Neural Networks (IJCNN), 1990, Vol. 2, pp. 331–336, San Diego, CA, 1990.
Kangas J. (1994): On the analysis of pattern sequences by self-organizing maps, Doctoral thesis, Helsinki University of Technology, Espoo, Finland
Kohonen T. (1982): Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69
Kohonen T. (1995). Self-organizing Maps. Springer-Verlag, Berlin
Kohonen, T., Hynninen, J., Kangas, J. and Laaksonen, J.: SOM_PAK. The Self-Organizing Map Program Package. Version 3.1 (April 7, 1995). Helsinki University of Technology, Laboratory of Computer and Information Science, 1995, http://www.cis.hut.fi/research/som-research/nnrc-programs.shtml.
Koskela, T., Varsta, M., Heikkonen, J. and Kaski, K.: Temporal sequence processing using recurrent SOM. In: Proceedings 2nd International Conference on Knowledge-Based Intelligent Engineering Systems, Adelaide, Australia, Vol. I, pp. 290–297, 1998.
Kaski, S.: Dimensionality reduction by random mapping: fast similarity computation for clustering. In: Proceedings IJCNN’98 International Joint Conference on Neural Networks, Anchorage, Alaska, May 4–9, 1998.
McClelland, J. L., Rumelhart, D. E. and the PDP Research Group.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. 1. Foundations, MIT Press, Cambridge,1986
McClelland, J. L., Rumelhart, D. E. and the PDP Research Group: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. 2. Psychological and Biological Models, MIT Press, Cambridge, 1986.
Varsta, M.: Self organizing maps in sequence processing. Dissertation, Department of Electrical and Communications Engineering, Helsinki University of Technology, 2002.
Vesanto, J., Himberg, J., Alhoniemi, E. and Parhankangas, J.: SOM toolbox for MATLAB 5. Helsinki University of Technology, Neural Networks Research Centre, Report A57, 2000, http://www.cis.hut.fi/projects/somtoolbox/
Voegtlin, T.: Context quantization and contextual self-organizing maps. In: Proceedings International Joint Conference on Neural Networks (IJCNN), 2000, Vol. 6, pp. 20–25, Piscataway, NJ, 2000
Voegtlin T. (2002): Recursive self-organizing maps. Neural Networks 15(8–9): 979–991
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hynna, K.I., Kaipainen, M. Activation-Based Recursive Self-Organising Maps: A General Formulation and Empirical Results. Neural Process Lett 24, 119–136 (2006). https://doi.org/10.1007/s11063-006-9015-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-006-9015-8