Abstract
A temporal extension of the Self-Organizing Map (SOM)is presented. The learning algorithm is based on self-reference, and is called Recursive SOM. This network learns local representations of the temporal context associated with a time series, and extends classical properties of SOM to time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. J. Chappell and J. G. Taylor. The temporal Kohonen map. Neural networks, 6: 441-445, 1993.
J. L. Elman. Finding structure in time. Cognitive Science, 14: 179-211, 1990.
N.R. Euliano and J.C. Principe. Spatio-temporal self-organizing feature maps. Proceedings of the ICNN, pages 1900-1905, 1996.
A. Hoekstra and M. Drossaers. An extended Kohonen feature map for sentence recognition. Proceedings of the ICANN, pages 404-407, 1993.
D. L. James and R. Miikkulainen. SARDNET: a self-organizing feature map for sequences. Advances in Neural Information Processing Systems, 7: 577-584, 1995.
J. Kangas. On the Analysis of Pattern Sequences by Self-Organizing Maps. Ph.D. Thesis, Helsinki University of Technology, 1994.
T. Kohonen. Self-Organizing Maps. Springer-Verlag, Berlin, 2nd edition, 1997.
K. Kopecz. Unsupervised learning of sequences on maps with lateral connectivity. Proceedings of the ICANN, pages 431-436, 1995.
T. Koskela, M. Varsta, J. Heikkonen, and K. Kaski. Time series prediction using recurrent SOM with local linear models. Int. J. of Knowledge-Based Intelligent Engineering Systems, 2(l): 60-68, 1998.
M.C. Mackey and Glass L. Oscillations and chaos in physiological control systems. Science, pages 197-287, 1977.
J. Vesanto. Using the som and local models in time-series prediction. In Proceedings of WSOM’97, pages 209-214, 1997.
T. Voegtlin. Context quantization and contextual self-organizing maps. In Proceedings of the IJCNN’2000, volume 6, pages 20-25, 2000.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag London Limited
About this paper
Cite this paper
Voegtlin, T., Dominey, P.F. (2001). Recursive Self-Organizing Maps. In: Advances in Self-Organising Maps. Springer, London. https://doi.org/10.1007/978-1-4471-0715-6_27
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0715-6_27
Publisher Name: Springer, London
Print ISBN: 978-1-85233-511-3
Online ISBN: 978-1-4471-0715-6
eBook Packages: Springer Book Archive